© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 810
    Prev
    Next
    INDEX
    Explanations

    possessive 's

    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
     レストラン
    -2.00
    ’
    -1.75
     necesarias
    -1.72
     jagged
    -1.70
     indep
    -1.67
    on
    -1.63
    麁
    -1.57
    ();
    -1.53
     wailing
    -1.52
    asanjo
    -1.48
    POSITIVE LOGITS
    亖
    2.06
    鹛
    2.05
     –
    2.03
    ໊
    2.02
    ↵↵
    1.91
    dienne
    1.82
    镦
    1.82
     architekt
    1.69
     tapi
    1.68
    휀
    1.68
    Activations Density 0.010%

    No Known Activations