© 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. 155543
    Prev
    Next
    INDEX
    Explanations

    predicting specific word completions

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

    work required or budget

    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
    ‌,
    0.48
    ედ
    0.44
    ,​
    0.43
    ці
    0.43
     cookbooks
    0.43
    تين
    0.42
     paler
    0.42
    <unused2113>
    0.42
     mélange
    0.41
    POSITIVE LOGITS
     a
    0.61
    nv
    0.50
    1
    0.49
    ymin
    0.47
     داشتن
    0.47
    linalg
    0.46
     ا
    0.46
    rl
    0.45
    ln
    0.45
    vidia
    0.45
    Activations Density 0.002%

    No Known Activations