© 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. 25781
    Prev
    Next
    INDEX
    Explanations

    references or citations

    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
     Bedürfn
    -0.84
     aimé
    -0.78
    '}';
    -0.71
     Conventional
    -0.71
    iness
    -0.71
    ias
    -0.71
    生地
    -0.70
    cin
    -0.70
     verzichten
    -0.69
    🛏
    -0.69
    POSITIVE LOGITS
     Վեր
    0.94
    Yuki
    0.84
     printf
    0.81
     directamente
    0.81
    BITDA
    0.80
    ît
    0.77
    ROUT
    0.77
    moire
    0.77
    פיה
    0.77
     quadr
    0.76
    Activations Density 0.104%

    No Known Activations