© 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. 101940
    Prev
    Next
    INDEX
    Explanations

    Leishmania, Application, Pochettino, Details, Harman

    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
     {
    -2.41
     But
    -2.25
    x
    -2.17
    的
    -2.14
    p
    -1.98
     ,
    -1.98
    2
    -1.86
     If
    -1.84
    Also
    -1.82
    ↵
    -1.80
    POSITIVE LOGITS
    蕺
    2.30
    Ꭳ
    2.28
    啣
    2.22
    酲
    2.20
     indiví
    2.20
    }}}{
    2.19
    殽
    2.14
    雠
    2.08
    鈊
    2.08
    鸲
    2.08
    Activations Density 0.000%

    No Known Activations