© 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. 30623
    Prev
    Next
    INDEX
    Explanations

    sans serif

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

    classification and specific topics

    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
     sensitization
    0.46
    षक
    0.45
    িতেছিল
    0.45
    Ꮁ
    0.44
     monetization
    0.44
    ಾನ್
    0.44
    catalyzed
    0.43
    コラボ
    0.43
     $($
    0.43
    iconductor
    0.42
    POSITIVE LOGITS
     uyg
    0.55
     Nós
    0.50
     Eleven
    0.48
     我們
    0.46
     Six
    0.46
     nós
    0.46
     Towards
    0.45
     Seven
    0.44
     Quite
    0.43
     Goy
    0.42
    Activations Density 0.000%

    No Known Activations