© 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. 220261
    Prev
    Next
    INDEX
    Explanations

    handles, HAR, application

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

    adhering to rules

    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
     編
    0.50
    鄧
    0.49
    exa
    0.48
    🥜
    0.47
    大學
    0.46
     આન
    0.46
     遅
    0.46
    ㄜ
    0.46
    Ꮇ
    0.45
    গুলোর
    0.44
    POSITIVE LOGITS
    ון
    0.55
     CLEAN
    0.53
     Shabb
    0.52
     پاک
    0.48
    ayv
    0.48
    perger
    0.46
     NEET
    0.46
     disappro
    0.45
    applicazione
    0.45
     scrutin
    0.44
    Activations Density 0.000%

    No Known Activations