© 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. 74272
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or specific words

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

    code blocks and specific symbols

    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
    萱
    0.38
    ]_
    0.38
     রোগে
    0.38
    M
    0.37
    眼中
    0.37
     Quando
    0.37
    玉
    0.37
    ors
    0.37
     instilled
    0.36
    Modifier
    0.36
    POSITIVE LOGITS
     ۱
    0.45
    １
    0.45
    ۰
    0.44
    ੧
    0.41
     народов
    0.39
    زمة
    0.37
    ۱
    0.37
    ۰۰
    0.37
     %,
    0.36
     جوړونکی
    0.36
    Activations Density 0.025%

    No Known Activations