© 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. 245438
    Prev
    Next
    INDEX
    Explanations

    phrases and compound nouns

    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
    ’
    0.61
    Difficulty
    0.48
    CHES
    0.48
    Telemetry
    0.48
    危害
    0.47
    মান
    0.47
    CHAR
    0.47
    平凡
    0.47
    ঠোর
    0.47
    二次
    0.47
    POSITIVE LOGITS
     기다
    0.54
     त्यांनी
    0.54
     следует
    0.52
     밤
    0.50
     ሴ
    0.49
     गर्भवती
    0.49
     것도
    0.49
    ordable
    0.48
     очередь
    0.48
     ソフト
    0.48
    Activations Density 0.000%

    No Known Activations