© 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. 253938
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     নৃত
    0.58
    လမ်း
    0.56
     ভরণ
    0.55
     equities
    0.50
    燜
    0.50
     ललित
    0.49
     riveting
    0.49
     Whisky
    0.49
    lexeme
    0.49
     मेजर
    0.49
    POSITIVE LOGITS
    ㅡ
    0.52
    к
    0.47
    ''(
    0.46
     tho
    0.46
    恶
    0.46
    k
    0.45
    (
    0.45
    Older
    0.45
    AW
    0.44
    s
    0.44
    Activations Density 0.001%

    No Known Activations