© 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. 194399
    Prev
    Next
    INDEX
    Explanations

    comparing things

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

    still home

    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
    veillance
    0.50
    셉
    0.46
    シティ
    0.46
    gevity
    0.44
    tive
    0.44
    ኡ
    0.44
    ropol
    0.44
     fractionation
    0.44
    volution
    0.44
    領導
    0.44
    POSITIVE LOGITS
     das
    0.46
     facendo
    0.46
     trag
    0.45
    خن
    0.45
     hann
    0.45
    #,
    0.45
     kedua
    0.44
    ’;
    0.44
    ,//
    0.44
     rav
    0.44
    Activations Density 0.001%

    No Known Activations