© 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. 54431
    Prev
    Next
    INDEX
    Explanations

    common phrases and noun compounds

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

    customer churn

    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
    ۸
    0.47
     با
    0.45
     Ports
    0.42
    با
    0.41
     meest
    0.41
    but
    0.41
     peripher
    0.41
    ۷
    0.40
    ۹
    0.40
    지만
    0.39
    POSITIVE LOGITS
     செய்தனர்
    0.46
     আগেই
    0.44
     तत्कालीन
    0.44
     ছিলোনা
    0.44
    安心して
    0.43
     গেলো
    0.43
    リスク
    0.43
     cytotoxicity
    0.42
     современной
    0.41
     pancreatic
    0.41
    Activations Density 0.002%

    No Known Activations