© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91867
    Prev
    Next
    INDEX
    Explanations

    explanation of rules and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ng
    0.57
    po
    0.57
     po
    0.52
     a
    0.47
     extra
    0.46
     passive
    0.45
     sensibles
    0.44
    ms
    0.44
     poaching
    0.43
    ker
    0.43
    POSITIVE LOGITS
     Биз
    0.51
    国务院
    0.48
     Roundtable
    0.46
    䐝
    0.46
     تجارت
    0.45
     рекла
    0.44
     Incorporated
    0.44
     الدولة
    0.44
     заработной
    0.43
    🏦
    0.43
    Activations Density 0.017%

    No Known Activations