© 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. 42282
    Prev
    Next
    INDEX
    Explanations

    copyright and source attribution

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

    copyright symbol year

    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
    ۔
    0.75
     formulas
    0.66
    ,
    0.64
    ?
    0.64
     enrichment
    0.61
    !
    0.59
    ።
    0.58
     enrich
    0.58
     was
    0.57
     enchant
    0.57
    POSITIVE LOGITS
    0
    0.76
    ка
    0.64
    raw
    0.62
    ca
    0.61
    íj
    0.58
    கடந்த
    0.58
    buscar
    0.57
    hình
    0.57
     கடந்த
    0.56
    ０
    0.55
    Activations Density 0.003%

    No Known Activations