© 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. 9310
    Prev
    Next
    INDEX
    Explanations

    private house pool

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

    Chandelier

    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
     ආකාර
    0.30
    軼
    0.29
     함수의
    0.29
     ممالک
    0.29
     societies
    0.28
    पचारिक
    0.28
     afectar
    0.28
     salarié
    0.28
    অপহরণ
    0.28
     accidens
    0.28
    POSITIVE LOGITS
    石
    0.32
     Stone
    0.32
     Little
    0.32
     Wood
    0.31
     Gu
    0.31
     石
    0.30
     Hill
    0.29
     Honey
    0.29
     T
    0.29
     stone
    0.29
    Activations Density 0.096%

    No Known Activations