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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40164
    Prev
    Next
    INDEX
    Explanations

    offer free shipping

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

    The neuron is detecting e-commerce style promotional text—i.e. retail/marketing copy (online sales pitches).

    oai_token-act-pair · o4-miniTriggered 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
     their
    -1.67
     people
    -1.41
     three
    -1.29
     очень
    -1.22
     four
    -1.20
    って言
    -1.20
    teclado
    -1.15
     now
    -1.14
     two
    -1.13
     дуже
    -1.09
    POSITIVE LOGITS
     الجلد
    1.49
     our
    1.26
     bpy
    1.23
     herbes
    1.19
     unseren
    1.17
     OCTOBER
    1.17
     Novembre
    1.15
     radeon
    1.13
     logements
    1.11
     also
    1.10
    Activations Density 0.037%

    No Known Activations