© 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. 105924
    Prev
    Next
    INDEX
    Explanations

    others believe

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

    room, military, kid, HR

    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
    3
    0.53
    ilen
    0.52
    izons
    0.48
     Pess
    0.48
    ı
    0.47
    하여
    0.46
    enschaft
    0.46
    cipline
    0.45
    /
    0.45
    pire
    0.44
    POSITIVE LOGITS
     trueMap
    0.52
    ᴄ
    0.51
    ዪ
    0.50
     setColor
    0.48
     addTo
    0.48
     シンプル
    0.47
     setId
    0.47
     防水
    0.46
    <unused2117>
    0.46
     frågor
    0.46
    Activations Density 0.000%

    No Known Activations