© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129056
    Prev
    Next
    INDEX
    Explanations

    pay and amounts professionalism

    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
    Negative Logits
    ੨
    0.46
     esche
    0.45
     업무
    0.45
    ੧
    0.43
    ng
    0.42
    gn
    0.42
    をも
    0.42
    description
    0.41
    eslint
    0.41
    eq
    0.40
    POSITIVE LOGITS
    Ply
    0.54
    Member
    0.50
    冰
    0.48
    Peek
    0.47
    িন্দু
    0.45
    री
    0.44
    Elvis
    0.44
    Acetoxy
    0.44
    ومی
    0.43
    Forgery
    0.43
    Activations Density 0.007%

    No Known Activations