© 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. 55851
    Prev
    Next
    INDEX
    Explanations

    the sports

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

    feline mystery grace, cancellation laws, software systems

    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
    quantile
    0.48
    痕
    0.47
    ৬
    0.46
    路径
    0.44
    ون
    0.43
    bru
    0.43
    ⋅
    0.43
     ･
    0.43
    人工智能
    0.43
    区块链
    0.43
    POSITIVE LOGITS
     !!,
    0.45
    abbam
    0.45
    ickets
    0.44
     Ettha
    0.44
     vutt
    0.44
     เลย
    0.44
    ноу
    0.43
     Trigon
    0.43
     Balliye
    0.43
    ueses
    0.42
    Activations Density 0.000%

    No Known Activations