© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137260
    Prev
    Next
    INDEX
    Explanations

    brands establish

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

    inferring structure, security responses, individual limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unusable
    0.46
     getDescription
    0.45
     resetButton
    0.44
     occasions
    0.44
    蟆
    0.44
    ットン
    0.43
     Thumbnail
    0.43
    윙
    0.42
     embank
    0.41
     addButton
    0.41
    POSITIVE LOGITS
    politics
    0.53
    apit
    0.48
    ön
    0.47
     paesi
    0.47
    augh
    0.46
    ua
    0.46
    Sigma
    0.46
     μέχρι
    0.46
     paralel
    0.45
     politics
    0.45
    Activations Density 0.001%

    No Known Activations