© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35311
    Prev
    Next
    INDEX
    Explanations

    listing or inclusion

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on mentions of “content” and related terms (creation, providers, creators, publishing, streaming).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    text related to advertising services, business promotion, and content provider opportunities.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    descriptions of digital media/online platforms where creators or businesses advertise, list, or promote content and services.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    خرید
    -0.99
     poliuret
    -0.98
    zędu
    -0.96
    購入
    -0.94
     potes
    -0.94
    มาะ
    -0.93
    [:,
    -0.89
     Auswahl
    -0.89
     Vainqueur
    -0.89
     Buying
    -0.86
    POSITIVE LOGITS
    の魅力
    1.06
    šti
    1.05
     secretario
    1.04
     tenu
    1.02
     خدمة
    1.00
     bene
    0.96
     enregistrer
    0.94
     créer
    0.94
    ffeine
    0.93
    beginning
    0.93
    Activations Density 0.072%

    No Known Activations