© 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. 51584
    Prev
    Next
    INDEX
    Explanations

    where conflict arises

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

    language and image models

    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
     multe
    0.55
    वर्ती
    0.53
    ">⁢</
    0.48
    ransport
    0.48
    瘧
    0.47
    ၎
    0.45
    ningen
    0.45
    転車
    0.45
    ande
    0.44
     remedial
    0.44
    POSITIVE LOGITS
     EI
    0.48
     Breaks
    0.48
    omores
    0.48
     DAW
    0.47
     milligrams
    0.46
    ി
    0.46
     aldığı
    0.46
    Input
    0.45
     Proceed
    0.45
     Elaina
    0.45
    Activations Density 0.000%

    No Known Activations