© 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-65K
    7. 55587
    Prev
    Next
    INDEX
    Explanations

    not just down

    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
    治疗
    0.54
    嬷
    0.54
     kitabı
    0.50
    阎
    0.49
    攻击
    0.49
    阴
    0.49
    教师
    0.48
    丛
    0.48
    ኔታ
    0.47
    ეც
    0.47
    POSITIVE LOGITS
     industries
    0.59
    -
    0.56
     of
    0.55
     -
    0.55
     Western
    0.55
     companies
    0.54
     industrial
    0.54
     manufacturers
    0.54
     enterprises
    0.52
    companies
    0.51
    Activations Density 0.008%

    No Known Activations