© 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. 64427
    Prev
    Next
    INDEX
    Explanations

    entire list, in each, in applied

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

    describing the AI "I"

    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
    s
    0.58
     your
    0.50
    Snow
    0.48
    Schneider
    0.48
    config
    0.48
     Snow
    0.48
     countries
    0.45
    C
    0.45
     Otto
    0.44
     Canada
    0.43
    POSITIVE LOGITS
     प्रकर
    0.54
    謄
    0.54
     пусто
    0.52
     ವಿಚಾರ
    0.51
    หลากหลาย
    0.51
     nameWithOwner
    0.49
     своё
    0.49
     दोषी
    0.49
     हिंसा
    0.48
    蛍光
    0.48
    Activations Density 0.000%

    No Known Activations