© 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. 22-GEMMASCOPE-RES-131K
    7. 73244
    Prev
    Next
    INDEX
    Explanations

    XML attributes and code elements

    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_22/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
    udere
    -1.09
    炻
    -1.03
    ucap
    -1.00
    fying
    -0.97
    nemen
    -0.97
    nisse
    -0.95
    adakan
    -0.95
     چیز
    -0.95
    tutup
    -0.93
    Ꮠ
    -0.93
    POSITIVE LOGITS
    ;
    1.05
     voltou
    1.02
     forteller
    0.98
     אחרי
    0.96
     Чтобы
    0.94
     escreveu
    0.92
     død
    0.91
     anunciou
    0.90
     setelah
    0.90
     criou
    0.90
    Activations Density 0.022%

    No Known Activations