© 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. 105692
    Prev
    Next
    INDEX
    Explanations

    such as; this calls; what is

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

    division, mathematical operations, code syntax

    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
     sådan
    0.52
     gezegd
    0.50
     ऐप
    0.48
    玾
    0.47
     kuni
    0.46
     گفته
    0.46
     कहने
    0.46
     නව
    0.45
     uitle
    0.45
     ആള
    0.44
    POSITIVE LOGITS
    as
    0.58
    is
    0.48
    είο
    0.47
    在
    0.47
    widehat
    0.46
    Авто
    0.45
    読み
    0.42
    ược
    0.42
    UER
    0.42
    ("+
    0.42
    Activations Density 0.000%

    No Known Activations