© 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. 31-GEMMASCOPE-2-RES-262K
    7. 8025
    Prev
    Next
    INDEX
    Explanations

    math notation and directions

    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
    ights
    0.52
    👜
    0.47
    侶
    0.47
    洶
    0.47
    iour
    0.46
    തിനാ
    0.46
     commencent
    0.46
    rews
    0.46
     दिन
    0.46
    այ
    0.45
    POSITIVE LOGITS
    Plate
    0.49
    an
    0.45
    Marketing
    0.45
    0
    0.45
    Birmingham
    0.45
     آ
    0.45
    Block
    0.44
    u
    0.44
    Design
    0.44
    corner
    0.44
    Activations Density 0.002%

    No Known Activations