© 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. 115073
    Prev
    Next
    INDEX
    Explanations

    Finding information and new things

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

    cleanest dirt, green light time

    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
    Blade
    0.46
     hometown
    0.42
     cứng
    0.42
     persist
    0.42
     fared
    0.42
    Diego
    0.41
     southeastern
    0.40
    ,
    0.40
    [,
    0.39
     storefront
    0.38
    POSITIVE LOGITS
     इसको
    0.46
    ائح
    0.44
    सेवक
    0.44
     रामचंद्र
    0.43
    णार
    0.42
    arquia
    0.42
     இன்று
    0.42
    ัท
    0.41
     Decorative
    0.41
     அதனை
    0.41
    Activations Density 0.005%

    No Known Activations