© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3394
    Prev
    Next
    INDEX
    Explanations

    headings and labels

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

    introduces notes or instructions

    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_53_width_65k_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
     \\
    0.50
    ”“
    0.44
     obwohl
    0.42
    \
    0.41
     :)
    0.41
    <h2>
    0.41
     例文帳に追加
    0.40
    ?\
    0.39
    !\
    0.39
     Ã
    0.38
    POSITIVE LOGITS
    NOTE
    0.81
    Примеча
    0.69
    WARNING
    0.68
    Note
    0.65
    RELATED
    0.63
    Spoiler
    0.61
    Warning
    0.61
    UPDATE
    0.61
     WARNING
    0.59
    TIP
    0.59
    Activations Density 0.003%

    No Known Activations