© 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. 197560
    Prev
    Next
    INDEX
    Explanations

    bridge driver

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

    technical instructions and configuration

    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
     wipers
    0.52
     pushed
    0.51
     слов
    0.50
     squeezed
    0.49
     झटका
    0.48
     ശക്ത
    0.48
     wrinkles
    0.47
     攵
    0.47
     ⏮
    0.47
     ধাক
    0.46
    POSITIVE LOGITS
    伝
    0.50
    DIG
    0.50
     dement
    0.48
     olen
    0.48
    綜合
    0.48
    in
    0.47
    Sar
    0.47
    n
    0.47
    Mutual
    0.46
    Past
    0.46
    Activations Density 0.000%

    No Known Activations