© 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. 65877
    Prev
    Next
    INDEX
    Explanations

    documentation and feedback requests

    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
    rody
    -0.81
     ситуация
    -0.81
    chsel
    -0.77
    stella
    -0.76
    sbereich
    -0.75
     escuchado
    -0.74
     bibl
    -0.74
    又是
    -0.73
     简介
    -0.73
     erik
    -0.71
    POSITIVE LOGITS
     this
    1.16
    anera
    0.92
     dieser
    0.92
    ایه
    0.89
    はこの
    0.88
     данной
    0.88
     этой
    0.88
    BorderFactory
    0.85
    yaw
    0.84
    ceived
    0.84
    Activations Density 0.065%

    No Known Activations