© 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. 84261
    Prev
    Next
    INDEX
    Explanations

    computer programs

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

    positions and PHP scripts

    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
    ICH
    0.48
    Memento
    0.46
    </h3>
    0.46
    <0x0D>
    0.44
     observes
    0.43
    閤
    0.43
    ubit
    0.43
    ⁢</
    0.42
    mdi
    0.42
     காண
    0.42
    POSITIVE LOGITS
     ವೇಳೆ
    0.54
     Scripts
    0.50
     จํานวน
    0.44
    اي
    0.43
     simpel
    0.43
     tyrannical
    0.42
     Dolls
    0.42
    ስቃ
    0.42
     hilfreich
    0.42
    ようやく
    0.42
    Activations Density 0.001%

    No Known Activations