© 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. 117980
    Prev
    Next
    INDEX
    Explanations

    section, lego, no time, certification, artificial heart

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

    Green Card, candidate, CYCLE ON, package main, Biological Filtration

    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
     pension
    0.55
     stră
    0.52
     sustained
    0.48
    مس
    0.47
     handing
    0.47
     conceptually
    0.47
    ं
    0.47
     recruitment
    0.47
     prognosis
    0.46
     conceptual
    0.46
    POSITIVE LOGITS
    勵
    0.49
    忝
    0.47
    我們的
    0.44
    咸
    0.44
    ತ್
    0.43
    xF
    0.43
     খেলে
    0.43
    性感
    0.43
    纏
    0.43
    DFC
    0.43
    Activations Density 0.000%

    No Known Activations