© 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-262K
    7. 81384
    Prev
    Next
    INDEX
    Explanations

    actual, gradient, θ, consequence

    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_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
    ipedia
    0.53
     translational
    0.50
     שא
    0.49
     entendimento
    0.49
    𒊏
    0.49
     ری
    0.47
     ہمس
    0.47
     शब्दा
    0.47
     Предпо
    0.47
     فهر
    0.47
    POSITIVE LOGITS
     want
    0.42
    쾰
    0.41
    有的
    0.41
     be
    0.40
    </u>
    0.39
    <0x10>
    0.38
     echte
    0.38
    EZ
    0.38
    Want
    0.38
     forget
    0.38
    Activations Density 0.002%

    No Known Activations