© 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. 40029
    Prev
    Next
    INDEX
    Explanations

    ! or ?

    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
    D
    -2.20
     человек
    -1.92
    s
    -1.86
    玉ねぎ
    -1.84
     our
    -1.82
     vårt
    -1.77
    ,”
    -1.76
    <td>
    -1.74
     espagne
    -1.68
     简约
    -1.67
    POSITIVE LOGITS
    蔦
    1.91
     ingenieros
    1.73
    話の
    1.72
    癀
    1.70
     combatir
    1.69
     admiten
    1.69
     afectados
    1.66
     weiterer
    1.65
     Ordinary
    1.64
     kapı
    1.64
    Activations Density 0.058%

    No Known Activations