© 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. 198512
    Prev
    Next
    INDEX
    Explanations

    area:cards:lawsuit:you:century:Rab:Uh:We:looks:

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

    clinical relevance, deep tech, AI

    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
     indu
    0.48
     د
    0.47
     ك
    0.47
     ද
    0.46
     enjoys
    0.46
     എല്ലാ
    0.45
     Está
    0.44
     någon
    0.44
     Swezey
    0.44
     ل
    0.44
    POSITIVE LOGITS
    empres
    0.49
    Austria
    0.48
    こちら
    0.47
    वरील
    0.46
    ણી
    0.46
    nexus
    0.46
    blur
    0.45
     तोड़ने
    0.45
    urs
    0.45
    ări
    0.44
    Activations Density 0.001%

    No Known Activations