© 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. 53319
    Prev
    Next
    INDEX
    Explanations

    less than or equal to

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

    Imperium; team; mystery

    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
    tz
    0.54
    t
    0.46
    tsv
    0.45
    क्स्ट
    0.45
    tx
    0.44
    endela
    0.44
    रक्षा
    0.44
    फ्र
    0.43
     रचना
    0.43
    ด
    0.43
    POSITIVE LOGITS
     принято
    0.50
     onsite
    0.48
     motoring
    0.47
     quali
    0.46
     prehistoric
    0.46
     testing
    0.44
     startup
    0.44
     alcoved
    0.44
     ahi
    0.44
    льку
    0.44
    Activations Density 0.000%

    No Known Activations