© 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. 78544
    Prev
    Next
    INDEX
    Explanations

    target Illustrator code

    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
    ف
    0.47
    ب
    0.45
     sheeting
    0.45
     howling
    0.44
    пен
    0.42
    ج
    0.42
    การ
    0.42
    $?
    0.41
    ק
    0.41
    embedding
    0.41
    POSITIVE LOGITS
     Многие
    0.50
    🥇
    0.48
    newTask
    0.46
    čenja
    0.45
     salidas
    0.45
     otáz
    0.44
    ModeBanner
    0.44
    skou
    0.43
    𒄩
    0.43
     mudah
    0.42
    Activations Density 0.001%

    No Known Activations