© 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. 729
    Prev
    Next
    INDEX
    Explanations

    hashtagged numbers and codes

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

    code blocks and markdown 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
     IntegerValue
    0.51
    ట్స్‌మన్
    0.46
    Aq
    0.44
     trials
    0.44
    strcmp
    0.44
    %";
    0.44
    dynamic
    0.43
    isinde
    0.43
    FREQ
    0.42
    imizin
    0.41
    POSITIVE LOGITS
    )}-\
    0.46
     lor
    0.43
    lor
    0.43
    git
    0.42
    feather
    0.41
    หน่อย
    0.41
     티
    0.40
     लता
    0.40
    桨
    0.40
     अंडा
    0.40
    Activations Density 0.000%

    No Known Activations