© 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. 238381
    Prev
    Next
    INDEX
    Explanations

    form below, disappeared following

    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
    kette
    0.45
    🧒
    0.45
    👧
    0.44
     menstruation
    0.44
    óso
    0.43
     ',',
    0.43
    లోని
    0.42
     `:`,
    0.42
     několika
    0.42
     ಹೃದಯ
    0.41
    POSITIVE LOGITS
    厂家
    0.55
    厂商
    0.54
     software
    0.49
     업체
    0.49
    软件
    0.49
     мастер
    0.48
    Enterprise
    0.47
    Manufacturers
    0.46
     online
    0.46
     suppliers
    0.46
    Activations Density 0.001%

    No Known Activations