© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15855
    Prev
    Next
    INDEX
    Explanations

    close

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
    ති
    0.52
    新たな
    0.52
    दूसरे
    0.50
    וג
    0.49
    ੁ
    0.49
    떠
    0.49
    codehaus
    0.49
    -}\
    0.49
    ::::::::
    0.48
     nuova
    0.48
    POSITIVE LOGITS
     sucking
    0.63
     каждому
    0.61
     jedem
    0.57
     suppressing
    0.56
     sneezing
    0.55
     pedestrians
    0.55
     omitting
    0.54
     aside
    0.53
     diatas
    0.53
     everything
    0.52
    Activations Density 0.000%

    No Known Activations