© 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. 105168
    Prev
    Next
    INDEX
    Explanations

    v6 cylinder engine

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

    inspect and cool

    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
     collectives
    0.67
     syndromes
    0.57
     multiplies
    0.57
    正则
    0.53
    ර්ග
    0.50
     encontrados
    0.50
     fluxes
    0.49
     杯
    0.49
     chargingStation
    0.49
     diagonals
    0.49
    POSITIVE LOGITS
    -
    0.54
     Xan
    0.50
     COVID
    0.47
     X
    0.47
     britann
    0.47
     FOR
    0.46
     XXX
    0.46
    BAR
    0.45
     SIGN
    0.45
    inth
    0.45
    Activations Density 0.001%

    No Known Activations