© 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. 190678
    Prev
    Next
    INDEX
    Explanations

    specific numbers and groupings

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

    buckle up

    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
    t
    0.54
     be
    0.52
     días
    0.51
    ’
    0.51
     ruth
    0.50
    !
    0.48
    ้าร
    0.47
     merciless
    0.47
    ?
    0.47
     can
    0.46
    POSITIVE LOGITS
    стема
    0.52
     Vj
    0.52
     சனி
    0.52
    సర్
    0.51
    valment
    0.51
     கல்வி
    0.51
     மாசுபாடு
    0.51
     மாசுபா
    0.50
    সংখ্য
    0.50
    ❽
    0.50
    Activations Density 0.001%

    No Known Activations