© 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. 64583
    Prev
    Next
    INDEX
    Explanations

    貓玩

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

    how things work or why

    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
    Соц
    0.53
     Biografie
    0.51
    Ги
    0.50
    Ри
    0.49
     ასევე
    0.47
     höher
    0.46
    Gesellschaft
    0.46
    리
    0.46
     Compost
    0.45
     grotesque
    0.45
    POSITIVE LOGITS
    ड्डी
    0.46
     summarizing
    0.45
    रल
    0.45
     JACKSON
    0.43
     commitment
    0.43
     disampaikan
    0.41
     designations
    0.41
     thầy
    0.41
    हमारी
    0.40
     resigning
    0.40
    Activations Density 0.000%

    No Known Activations