© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 149882
    Prev
    Next
    INDEX
    Explanations

    instructions, advice, or statements

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

    daily Scrum, serial dilution, null space

    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
    Negative Logits
     vždy
    0.52
    琺
    0.51
    gewood
    0.49
    好
    0.49
     rooftops
    0.48
     ግ
    0.48
     желу
    0.47
     السب
    0.46
     станда
    0.46
     دليل
    0.46
    POSITIVE LOGITS
    EL
    0.55
    HTTP
    0.48
     Incident
    0.47
    Moment
    0.47
    TS
    0.47
    KT
    0.47
    Y
    0.46
    HA
    0.45
     forman
    0.45
     Moment
    0.45
    Activations Density 0.001%

    No Known Activations