© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77627
    Prev
    Next
    INDEX
    Explanations

    understanding why specific structures build

    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
    )$\
    0.45
    your
    0.45
    İ
    0.45
    こちら
    0.44
     yur
    0.44
    LANG
    0.43
     Phần
    0.43
     NJ
    0.42
    箕
    0.42
     Pennsylvania
    0.42
    POSITIVE LOGITS
    heits
    0.44
     динами
    0.43
     ≠
    0.42
    рует
    0.42
     be
    0.42
    acod
    0.41
    eron
    0.41
    herence
    0.41
    ري
    0.41
    водить
    0.41
    Activations Density 0.000%

    No Known Activations