© 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. 16-GEMMASCOPE-2-RES-16K
    7. 539
    Prev
    Next
    INDEX
    Explanations

    numbers, instructions, and listing items

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

    multi-script characters

    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_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OnClick
    0.46
    ৫
    0.42
    Default
    0.41
    FontSize
    0.40
    Current
    0.39
    خدام
    0.39
    Message
    0.39
    Status
    0.38
    UserDetails
    0.38
    GetInt
    0.38
    POSITIVE LOGITS
    기
    0.53
    ation
    0.52
    ب
    0.51
    an
    0.51
    a
    0.49
    ే
    0.47
    ం
    0.47
    ar
    0.45
    다면
    0.44
    며
    0.44
    Activations Density 0.022%

    No Known Activations