© 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. 71107
    Prev
    Next
    INDEX
    Explanations

    appointments suggested

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

    requires computational resources

    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
     viscos
    0.50
     milliliters
    0.49
     comorbidities
    0.46
     fractions
    0.42
     horns
    0.42
    ombres
    0.42
    一
    0.42
     auditors
    0.42
    していて
    0.42
     fibers
    0.41
    POSITIVE LOGITS
     ಪಡೆಯ
    0.52
    CLUD
    0.51
    ান
    0.50
     Lumpur
    0.50
    తర
    0.48
    弇
    0.48
    ষ্ঠ
    0.47
    SERVATION
    0.47
    ("["
    0.46
    rio
    0.46
    Activations Density 0.001%

    No Known Activations