© 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. 37399
    Prev
    Next
    INDEX
    Explanations

    mathematical coding and statistics

    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
    ry
    0.44
     answers
    0.42
     Зна
    0.41
    ;
    0.41
     undeniably
    0.39
     incredibly
    0.39
    scratch
    0.39
     ironically
    0.39
    Ⲣ
    0.39
    uman
    0.39
    POSITIVE LOGITS
     బ్యాంకు
    0.47
     বাংলায়
    0.47
     brunâtre
    0.46
    魧
    0.46
     বাংলায়
    0.45
     요거
    0.45
    媧
    0.45
    㑬
    0.44
     अभ्यर्थ
    0.43
     స్థాయిలో
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.