© 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. 15010
    Prev
    Next
    INDEX
    Explanations

    built-in features and components

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

    essential qualities

    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
    чина
    0.55
    мас
    0.55
    лизация
    0.52
    lcii
    0.52
    гаа
    0.50
    エリア
    0.50
     полной
    0.49
    外
    0.49
     பின்ப
    0.49
     FULLER
    0.48
    POSITIVE LOGITS
     inherent
    1.05
     intrinsic
    0.93
     intrinsically
    0.84
     inherently
    0.83
    intrinsic
    0.80
    embedded
    0.73
    Intrinsic
    0.73
    inher
    0.71
     embedded
    0.70
     inbuilt
    0.69
    Activations Density 0.044%

    No Known Activations