© 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. 87431
    Prev
    Next
    INDEX
    Explanations

    finish / finished

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

    newer Z-mount cameras

    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
    :.
    0.53
    number
    0.48
    tze
    0.48
     Vigo
    0.47
     mito
    0.46
    banana
    0.46
    เชื้อ
    0.45
    an
    0.44
    usern
    0.44
    loc
    0.43
    POSITIVE LOGITS
    出
    0.49
    ئ
    0.47
    是
    0.45
     ہوج
    0.44
    出した
    0.44
    マト
    0.43
    始
    0.43
    を
    0.41
    講
    0.41
    呈現
    0.41
    Activations Density 0.000%

    No Known Activations