© 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. 41180
    Prev
    Next
    INDEX
    Explanations

    formyl peptides

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

    from now on

    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
    ي
    0.53
    جي
    0.46
    精密
    0.46
     অসম্ভব
    0.45
     उल्टा
    0.45
    ու
    0.45
    合成
    0.45
    тру
    0.44
     хрони
    0.43
    澗
    0.43
    POSITIVE LOGITS
     rails
    0.53
     pastries
    0.53
     excursions
    0.49
     cheers
    0.48
     Gew
    0.48
     railings
    0.47
     พัน
    0.47
     trips
    0.45
    nung
    0.45
     bubbles
    0.45
    Activations Density 0.000%

    No Known Activations