© 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. 158969
    Prev
    Next
    INDEX
    Explanations

    contact address

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

    economic accessibility and resources

    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
    :
    0.61
    ;
    0.48
    .
    0.47
     ntawm
    0.46
    symbol
    0.45
    0.45
    5
    0.45
    \}_{
    0.45
     h
    0.44
    http
    0.44
    POSITIVE LOGITS
     연락
    0.55
     첫
    0.54
     처음
    0.53
     영향을
    0.52
    胭
    0.52
     두
    0.50
     раскры
    0.50
    屒
    0.49
    玦
    0.49
     दो
    0.49
    Activations Density 0.000%

    No Known Activations