© 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. 204320
    Prev
    Next
    INDEX
    Explanations

    sanitation, manufacturing, flyer

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

    modify, Mix, mimics, Gift, stereotype

    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
    ٹ
    0.48
     কোনো
    0.46
     ઇચ્છ
    0.46
     কোনও
    0.46
     আঁ
    0.45
     کوچ
    0.45
     વ્યક્તિ
    0.45
     বিশ্বাস
    0.44
    altz
    0.44
    random
    0.43
    POSITIVE LOGITS
     Differentiation
    0.55
     Diffraction
    0.53
    㧕
    0.50
    वीस
    0.50
     sest
    0.48
    긔
    0.48
     Synchronization
    0.45
    \"
    0.44
     Controversy
    0.44
     innebär
    0.44
    Activations Density 0.000%

    No Known Activations