© 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. 21235
    Prev
    Next
    INDEX
    Explanations

    identifiers and source attributions

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

    indicated in brackets

    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
    ž
    0.47
    .
    0.46
    era
    0.46
    he
    0.45
    ua
    0.44
    وه
    0.44
    —
    0.44
    -
    0.43
    č
    0.43
    set
    0.43
    POSITIVE LOGITS
    hatiti
    0.46
     pathophys
    0.46
     detd
    0.44
     ద్వారా
    0.44
    ዐይን
    0.44
     atak
    0.43
     ძალი
    0.43
     kehnd
    0.43
    乸
    0.43
    تدائي
    0.43
    Activations Density 0.000%

    No Known Activations