© 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. 31-GEMMASCOPE-2-RES-16K
    7. 14823
    Prev
    Next
    INDEX
    Explanations

    separators; list items

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

    comma separated items

    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_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
    一些
    0.50
    ορ
    0.47
    ==="
    0.46
     alguns
    0.42
     parseInt
    0.41
     Kanada
    0.40
    Ꮼ
    0.40
     mati
    0.40
    ქვს
    0.39
     humankind
    0.39
    POSITIVE LOGITS
    (',');
    0.41
    Ễ
    0.40
    ançois
    0.40
    Wedgwood
    0.39
     Vessel
    0.38
    蛉
    0.38
    Details
    0.37
    BUNDLE
    0.37
    (':')[
    0.36
    Ộ
    0.36
    Activations Density 0.002%

    No Known Activations