© 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. 64745
    Prev
    Next
    INDEX
    Explanations

    coding attributes and values

    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
     纳
    -0.90
    rtx
    -0.82
     县
    -0.81
     注意
    -0.78
     Monographs
    -0.75
    鬓
    -0.75
     for
    -0.74
    caucasian
    -0.73
     Med
    -0.73
    也可
    -0.72
    POSITIVE LOGITS
     ответствен
    0.89
     Kebijakan
    0.85
    捽
    0.83
    entiel
    0.82
    geocode
    0.80
     Fähig
    0.80
    alisis
    0.79
     Meilleures
    0.79
     данной
    0.79
     Politique
    0.79
    Activations Density 0.142%

    No Known Activations