© 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. 133589
    Prev
    Next
    INDEX
    Explanations

    % organic

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

    list of clauses and items

    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
     ghế
    0.51
     milioni
    0.50
     balanced
    0.49
     caudal
    0.49
     kerosene
    0.48
    萠
    0.48
     Balance
    0.48
     comerciantes
    0.47
     कारक
    0.47
    萆
    0.47
    POSITIVE LOGITS
    ih
    0.50
    dun
    0.47
    dus
    0.46
    ensively
    0.46
    br
    0.46
    well
    0.46
    diving
    0.45
    rology
    0.45
    ally
    0.44
    rolog
    0.44
    Activations Density 0.001%

    No Known Activations