© 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-65K
    7. 54360
    Prev
    Next
    INDEX
    Explanations

    body and structural elements

    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
    zący
    0.39
    Revision
    0.38
    levelname
    0.37
     revision
    0.37
    닷
    0.36
    revision
    0.36
     अस्थायी
    0.36
    riage
    0.35
    Simon
    0.35
    윌
    0.35
    POSITIVE LOGITS
     body
    0.62
    Body
    0.56
     BODY
    0.55
     Body
    0.52
    BODY
    0.50
    body
    0.48
    FromBody
    0.46
    uerpo
    0.46
     contentView
    0.43
    本体
    0.42
    Activations Density 0.110%

    No Known Activations