© 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. 200567
    Prev
    Next
    INDEX
    Explanations

    outfit, costumes, sushi

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

    JavaScript code and dependencies

    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
     preempt
    0.57
     MPL
    0.49
     PES
    0.47
     FUT
    0.47
     hoisting
    0.47
     KM
    0.46
     RAID
    0.46
     Į
    0.46
     MPM
    0.46
     hoisted
    0.46
    POSITIVE LOGITS
    ного
    0.51
    ние
    0.50
    产生
    0.50
    认
    0.50
    轮回
    0.48
    篇
    0.48
    ление
    0.48
    し
    0.47
    努
    0.47
    赠
    0.47
    Activations Density 0.000%

    No Known Activations