© 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. 52678
    Prev
    Next
    INDEX
    Explanations

    opening quotation marks

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

    opening quotation marks

    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
     collocation
    0.35
     결과
    0.33
     ትንሽ
    0.33
     scarcity
    0.32
     korrekt
    0.32
     నీ
    0.32
     ਬ
    0.31
    赋值
    0.31
     memset
    0.31
     biops
    0.31
    POSITIVE LOGITS
    hauses
    0.41
    .[/
    0.39
     принято
    0.39
     என்று
    0.38
     இருப்பதாக
    0.36
     фильм
    0.36
    ון
    0.36
     প্রসঙ্গে
    0.36
    .],
    0.36
    .),
    0.36
    Activations Density 0.015%

    No Known Activations