© 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. 97153
    Prev
    Next
    INDEX
    Explanations

    is independent

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

    direct service

    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
    รษฐ
    0.54
     LOTRAchievement
    0.52
     Audience
    0.52
    HOBBIT
    0.52
     円
    0.51
     Substitution
    0.51
     गाली
    0.51
    बंधनाच्या
    0.51
     짧
    0.51
    /*!
    0.50
    POSITIVE LOGITS
    decor
    0.46
     Edel
    0.46
     vertex
    0.44
    يت
    0.44
     cladding
    0.44
    0.44
    K
    0.43
    敝
    0.43
    áticas
    0.43
    ,
    0.43
    Activations Density 0.001%

    No Known Activations