© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 133897
    Prev
    Next
    INDEX
    Explanations

    exhaust fan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    髅
    0.48
     учащихся
    0.46
     selectInput
    0.45
    нансо
    0.43
    "),],
    0.43
    厝
    0.43
     ছাত্রদের
    0.43
    itriangular
    0.41
     ベース
    0.41
    woorden
    0.41
    POSITIVE LOGITS
     '
    0.48
     ('
    0.42
    sing
    0.42
    anim
    0.42
    present
    0.41
    bench
    0.41
     Bench
    0.41
    ond
    0.40
    man
    0.40
    ini
    0.40
    Activations Density 0.000%

    No Known Activations