© 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. 199077
    Prev
    Next
    INDEX
    Explanations

    iOS device

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

    comparisons of magnitude and proportion

    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
     ansiedad
    0.59
     după
    0.49
     ආ
    0.48
     diarrh
    0.47
     dupa
    0.47
     involunt
    0.47
     después
    0.46
     известно
    0.46
     regres
    0.46
     kaps
    0.45
    POSITIVE LOGITS
    eroy
    0.47
    Distribution
    0.46
    <
    0.46
    Vari
    0.44
    Repartition
    0.44
    クマ
    0.43
    Distrib
    0.43
     supernovae
    0.43
    ajú
    0.42
    াধিকার
    0.42
    Activations Density 0.002%

    No Known Activations