© 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. 63912
    Prev
    Next
    INDEX
    Explanations

    first one I picked up

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

    commentary, Bridge, Collider, operator

    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
    socketState
    0.52
     اسمه
    0.49
    ♚
    0.49
     человеком
    0.48
    ColumnKind
    0.48
     Temps
    0.47
     softwares
    0.47
    の名前
    0.47
     компаний
    0.46
     Playhouse
    0.46
    POSITIVE LOGITS
    log
    0.47
    சிற
    0.46
    在
    0.46
     in
    0.44
    each
    0.44
    g
    0.44
    گاه
    0.43
    nob
    0.43
    ib
    0.43
    ringing
    0.43
    Activations Density 0.000%

    No Known Activations