© 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. 31-GEMMASCOPE-2-RES-65K
    7. 15260
    Prev
    Next
    INDEX
    Explanations

    formulas for percentage calculation

    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_31_width_65k_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
     мони
    0.50
    KindOf
    0.46
    嘧
    0.45
     вашего
    0.45
    ronique
    0.43
    Cellphone
    0.42
    ohid
    0.41
    簟
    0.41
    手机
    0.41
    simmons
    0.41
    POSITIVE LOGITS
     It
    0.44
     ایسے
    0.44
    1
    0.42
    ad
    0.42
    <start_of_image>
    0.39
     jeste
    0.39
    in
    0.38
     oni
    0.37
     ponder
    0.36
     fervor
    0.36
    Activations Density 0.005%

    No Known Activations