© 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. 55309
    Prev
    Next
    INDEX
    Explanations

    brain followed by words

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

    brain damage

    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
    Class
    0.54
    Type
    0.50
    Processor
    0.50
    Spread
    0.49
    へ
    0.47
    Name
    0.46
    fit
    0.46
    bordered
    0.46
    Value
    0.46
    Leave
    0.46
    POSITIVE LOGITS
    橇
    0.52
     intuit
    0.50
     bicarbon
    0.49
    铬
    0.44
    湟
    0.43
     Munich
    0.43
     tonel
    0.43
     Esch
    0.43
    橥
    0.43
     首先
    0.42
    Activations Density 0.000%

    No Known Activations