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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48902
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    urgency, stakes, consequences, hacker, perspective

    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
    Not in Any Lists

    No Comments

    Negative Logits
    xanth
    0.48
     eutectic
    0.47
    bout
    0.47
    ˙
    0.46
    w
    0.46
    morph
    0.45
    옥
    0.45
    fers
    0.44
    mutable
    0.44
    <unused60>
    0.44
    POSITIVE LOGITS
    িনা
    0.51
    人們
    0.45
     đáo
    0.44
    鞦
    0.44
    飥
    0.44
     chiến
    0.43
     různých
    0.43
    當中
    0.42
     truyền
    0.42
    साना
    0.42
    Activations Density 0.000%

    No Known Activations