© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127416
    Prev
    Next
    INDEX
    Explanations

    business and legal terms

    np_acts-logits-general · gemini-2.5-flash-lite

    (LP) or 'gothic metal'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تين
    0.57
    t
    0.46
     يه
    0.46
    rolo
    0.45
    ت
    0.45
    CTION
    0.44
    historic
    0.44
    title
    0.44
    section
    0.43
    Pear
    0.43
    POSITIVE LOGITS
     claras
    0.48
     elegans
    0.46
    倨
    0.46
     Accounts
    0.46
    മ്
    0.45
     раху
    0.45
     अकाउंट
    0.45
     faiblement
    0.45
    ικών
    0.44
     vacuna
    0.44
    Activations Density 0.001%

    No Known Activations