© 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. 41-GEMMASCOPE-2-RES-262K
    7. 100108
    Prev
    Next
    INDEX
    Explanations

    year, date, number

    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_all/layer_41_width_262k_l0_big
    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
     billion
    0.41
    billion
    0.38
    semibold
    0.38
    ₵
    0.37
    桜
    0.36
    phenyl
    0.34
     Billion
    0.34
    mins
    0.33
     कब्रिस्तान
    0.33
    obenzene
    0.32
    POSITIVE LOGITS
     mettre
    0.73
     мяг
    0.65
    Mostrar
    0.63
     Мы
    0.62
     mettant
    0.62
     Μ
    0.62
     М
    0.60
     miedo
    0.58
     мы
    0.58
     maladies
    0.58
    Activations Density 0.006%

    No Known Activations