© 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. 112552
    Prev
    Next
    INDEX
    Explanations

    locomotor activity, curl up

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

    book flights

    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
     Unemployment
    0.48
    𝘳
    0.47
     Charity
    0.46
    rogation
    0.46
    scriber
    0.46
     eer
    0.45
     Bees
    0.45
    ,’’
    0.44
    urrection
    0.44
    媤
    0.44
    POSITIVE LOGITS
    納
    0.50
     khả
    0.47
     eingeb
    0.46
     sẽ
    0.44
     состоится
    0.43
    瑪
    0.43
    Routing
    0.42
    凱
    0.42
     iesp
    0.42
    ខាង
    0.41
    Activations Density 0.003%

    No Known Activations