© 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. 30494
    Prev
    Next
    INDEX
    Explanations

    hearty steaks

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

    love, tragedy, and complexity

    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
     fenders
    0.48
    工艺
    0.47
     fabrics
    0.46
    ु
    0.46
    ेंट्स
    0.45
    Produce
    0.44
     stents
    0.42
     deities
    0.42
     ventilators
    0.42
     элект
    0.41
    POSITIVE LOGITS
     Nunca
    0.55
    🥖
    0.52
     segundo
    0.52
    🥣
    0.52
    kowej
    0.51
    㠃
    0.49
     secondo
    0.49
     procent
    0.49
     IndexError
    0.48
    autocon
    0.48
    Activations Density 0.000%

    No Known Activations