© 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. 101328
    Prev
    Next
    INDEX
    Explanations

    loyalty, mobile, ultimately, Globe, Blue, west

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

    platforms, prevents, waiting, not, village, answer, encounter

    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
     높아
    0.55
     Таким
    0.52
     ಸುದ್ದ
    0.52
     높
    0.50
    వేశ
    0.48
     순간
    0.47
     Администра
    0.47
     ২০১
    0.47
     සිට
    0.47
     വനി
    0.46
    POSITIVE LOGITS
     archive
    0.49
     Dating
    0.47
     lasso
    0.46
     Enzyme
    0.44
     muñ
    0.44
    大
    0.44
    在
    0.44
     uncooked
    0.43
     enzymes
    0.42
     inú
    0.42
    Activations Density 0.000%

    No Known Activations