© 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. 45521
    Prev
    Next
    INDEX
    Explanations

    not offer

    np_acts-logits-general · gemini-2.5-flash-lite

    computer commands and system addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    acağız
    0.57
    është
    0.54
    翱
    0.52
    微软雅黑
    0.51
    𝒂
    0.50
    addKill
    0.50
     eksper
    0.49
     ajuda
    0.48
    ću
    0.48
    ıkları
    0.48
    POSITIVE LOGITS
     tourn
    0.43
    ಾರ
    0.42
    代謝
    0.39
    も見
    0.38
    西洋
    0.38
     उन्ह
    0.38
     vasodilator
    0.38
    沇
    0.38
     streptomycin
    0.37
     পৰ
    0.37
    Activations Density 0.000%

    No Known Activations