© 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. 77395
    Prev
    Next
    INDEX
    Explanations

    Kenmare offers

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

    API, databases, and web app builders

    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
     Recherches
    0.44
     röm
    0.42
     hourglass
    0.39
     dicion
    0.39
     aquare
    0.39
     gewisse
    0.38
     mith
    0.38
     ~/.
    0.38
     especialmente
    0.38
     chh
    0.38
    POSITIVE LOGITS
     Evanston
    0.46
    🫶
    0.46
     Shopify
    0.45
     Joanne
    0.44
     Fallout
    0.44
    cloudfront
    0.44
     Equity
    0.43
    नाक
    0.43
    storybook
    0.43
     Bryant
    0.42
    Activations Density 0.009%

    No Known Activations