© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84527
    Prev
    Next
    INDEX
    Explanations

    html span tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     différents
    -2.00
    🫴
    -1.93
    骉
    -1.81
     nieuwe
    -1.80
    𓁹
    -1.77
     ventilación
    -1.70
     très
    -1.68
    🫅
    -1.65
    で使
    -1.65
     bardzo
    -1.65
    POSITIVE LOGITS
    e
    2.02
    ⦊
    1.95
    .​
    1.92
    When
    1.91
    To
    1.91
    </td>
    1.88
     blistering
    1.77
     FetchType
    1.67
    唷
    1.64
    饪
    1.63
    Activations Density 0.008%

    No Known Activations