© 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. 34-GEMMASCOPE-RES-131K
    7. 65234
    Prev
    Next
    INDEX
    Explanations

    Foundation license agreements

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

    The neuron fires on license‐related boilerplate terms (e.g. “license,” “licensed,” copyright notices).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    anners
    -0.73
     Merc
    -0.71
    vajú
    -0.69
     formulae
    -0.69
    箴
    -0.67
    Ƞ
    -0.66
     Józef
    -0.65
     מִ
    -0.65
    ۬
    -0.65
    连续
    -0.64
    POSITIVE LOGITS
    buster
    0.73
    рев
    0.70
     Kuo
    0.69
     amending
    0.68
     Dispon
    0.68
    غات
    0.68
    belline
    0.67
    ynia
    0.66
     eti
    0.65
     Bring
    0.65
    Activations Density 0.044%

    No Known Activations