© 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. 24140
    Prev
    Next
    INDEX
    Explanations

    times, ages, or periods

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

    service version detection

    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
    പി
    0.57
    몇
    0.54
    ン
    0.50
    сё
    0.47
    Johann
    0.47
     Certainly
    0.46
    ษัท
    0.46
    <h2>
    0.46
     Significance
    0.46
     enorme
    0.45
    POSITIVE LOGITS
    isAuthenticated
    0.54
     পক্ষ
    0.48
     predation
    0.46
     _$
    0.46
    accessToken
    0.45
    )$;
    0.45
     perished
    0.45
    )$:
    0.45
    installation
    0.44
     questionable
    0.44
    Activations Density 0.000%

    No Known Activations