© 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. 114368
    Prev
    Next
    INDEX
    Explanations

    phrasal punctuation and conjunctions

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

    optimized and capture essence

    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
     مجموعة
    0.56
     bahagian
    0.54
     hukuk
    0.50
     kunna
    0.49
     المنا
    0.49
     منا
    0.47
    ඔ
    0.47
     التن
    0.46
     इसके
    0.46
     điều
    0.46
    POSITIVE LOGITS
    p
    0.48
    pch
    0.46
    x
    0.45
    릇
    0.44
    throws
    0.44
    람
    0.44
    ลาส
    0.44
    内
    0.44
    Launcher
    0.43
    鞘
    0.42
    Activations Density 0.000%

    No Known Activations