© 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. 228355
    Prev
    Next
    INDEX
    Explanations

    performance and progress

    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
    äuser
    0.50
    idiu
    0.48
    weekday
    0.46
     対象
    0.45
     追加
    0.44
    </strong>
    0.44
    ussen
    0.43
     {
    0.43
     裏
    0.43
     {$
    0.43
    POSITIVE LOGITS
    髡
    0.54
    ग्
    0.52
    Philos
    0.48
    و
    0.48
    ون
    0.46
    擒
    0.44
     পাইয়া
    0.44
    竣
    0.44
    Fla
    0.44
    chic
    0.43
    Activations Density 0.000%

    No Known Activations