© 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. 12498
    Prev
    Next
    INDEX
    Explanations

    code and labels

    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
    cccnc
    0.46
     স্থলে
    0.46
     jTextField
    0.45
    jTextField
    0.45
    jButton
    0.42
     jButton
    0.41
    蠶
    0.41
     MNR
    0.40
    ensa
    0.40
    ષ્ણા
    0.40
    POSITIVE LOGITS
     svg
    0.38
    =
    0.38
    ws
    0.37
     μπο
    0.37
    ={
    0.37
    给定
    0.36
    '],
    0.36
     কোলে
    0.35
     coincidence
    0.35
     brushed
    0.35
    Activations Density 0.000%

    No Known Activations