© 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. 25273
    Prev
    Next
    INDEX
    Explanations

    quoted text delimiters

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

    code punctuation

    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
    。「
    0.50
    );//
    0.49
    َة
    0.49
    嗎
    0.49
    。《
    0.48
     еле
    0.48
    ERRORTYPE
    0.48
    ؟.
    0.48
    ();//
    0.47
    。『
    0.47
    POSITIVE LOGITS
    s
    0.54
    d
    0.53
    -
    0.50
    ised
    0.48
     that
    0.47
    ish
    0.46
    on
    0.46
     Pid
    0.44
     associating
    0.44
     Quy
    0.44
    Activations Density 0.000%

    No Known Activations