© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5751
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     bencana
    0.85
    <end_of_turn>
    0.84
     temptations
    0.81
    顿
    0.79
     especificar
    0.78
    案内
    0.77
    Guru
    0.77
     सांगितलं
    0.77
     Severity
    0.77
     décès
    0.77
    POSITIVE LOGITS
    In
    0.79
    ());
    0.73
    (\
    0.68
    在这个
    0.67
    Elsewhere
    0.63
    ager
    0.62
    $("
    0.62
    В
    0.62
    When
    0.61
    Java
    0.61
    Activations Density 0.014%

    No Known Activations