© 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-65K
    7. 56070
    Prev
    Next
    INDEX
    Explanations

    fluctuations

    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_65k_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
    a
    0.61
    on
    0.60
    un
    0.54
     The
    0.53
    ir
    0.49
     M
    0.48
    وا
    0.48
    s
    0.47
     a
    0.47
    it
    0.46
    POSITIVE LOGITS
     Đó
    0.55
     хирур
    0.49
     subtracted
    0.46
     gouttes
    0.44
     cero
    0.44
     конститу
    0.44
    вки
    0.44
     хірур
    0.44
     минера
    0.43
    ⠑
    0.43
    Activations Density 0.028%

    No Known Activations