© 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. 200644
    Prev
    Next
    INDEX
    Explanations

    energy and jobs

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

    symbols and code delimiters

    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
    .
    0.51
    SS
    0.45
    Pretty
    0.45
    *
    0.44
    MS
    0.44
     Pretty
    0.44
    0.43
    UL
    0.42
    高校
    0.42
    ITH
    0.42
    POSITIVE LOGITS
    畞
    0.48
     پیشنه
    0.48
     ამ
    0.47
     בה
    0.47
     Botanical
    0.47
    াত্ম
    0.46
     scathing
    0.46
     sizz
    0.46
     സഞ്ച
    0.46
    quả
    0.46
    Activations Density 0.000%

    No Known Activations