© 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. 212104
    Prev
    Next
    INDEX
    Explanations

    source or characteristic

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

    version numbers and sequences

    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
    га
    0.54
    ка
    0.53
     WOULD
    0.43
    ке
    0.40
    鯤
    0.40
     спорттук
    0.40
    ীন
    0.40
     недоста
    0.40
    ৰ
    0.39
    у
    0.39
    POSITIVE LOGITS
     heterogeneity
    0.59
     séqu
    0.51
     ethnicity
    0.49
     världen
    0.47
     algorithms
    0.47
    sequence
    0.46
     ដើម្បី
    0.46
     homogeneity
    0.46
     semantics
    0.46
    alphabet
    0.46
    Activations Density 0.000%

    No Known Activations