© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199320
    Prev
    Next
    INDEX
    Explanations

    want to update, planning

    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
    fold
    0.49
    T
    0.47
    set
    0.47
    file
    0.47
    config
    0.46
    J
    0.46
    F
    0.45
    ian
    0.44
    N
    0.44
    C
    0.44
    POSITIVE LOGITS
     protezione
    0.54
     পরিবর্তনের
    0.54
     redesigned
    0.54
     protecting
    0.52
    DesIP
    0.51
     smothered
    0.49
    routingHeader
    0.48
    𝟬
    0.48
     intervención
    0.48
     BLUEN
    0.47
    Activations Density 0.002%

    No Known Activations