© 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. 19260
    Prev
    Next
    INDEX
    Explanations

    sentence endings like periods and ellipses

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

    title, description, or code formatting

    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
    à
    0.42
    subfloat
    0.41
    ais
    0.39
    ambra
    0.39
     차
    0.38
    abila
    0.38
     Nasıl
    0.38
     ۱۳۹
    0.38
     dashing
    0.38
     Acerca
    0.38
    POSITIVE LOGITS
    pointee
    0.42
     chemists
    0.40
     Knoten
    0.40
    __:
    0.40
     नपु
    0.40
    হারা
    0.39
     infert
    0.39
     chemically
    0.38
     cổ
    0.38
    目錄
    0.37
    Activations Density 0.003%

    No Known Activations