© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 253667
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    0.47
    dokument
    0.47
     abusers
    0.46
    maschinen
    0.45
     called
    0.44
    を用意
    0.44
    Administ
    0.44
    期刊
    0.43
    顔
    0.43
     abusive
    0.43
    POSITIVE LOGITS
     တော့
    0.51
     ϒ
    0.50
     Роб
    0.46
     గత
    0.46
     మూడు
    0.46
     Oats
    0.46
     六
    0.46
     সাইফুদ্দিন
    0.46
     संक्रमण
    0.45
    yii
    0.45
    Activations Density 0.001%

    No Known Activations