© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4837
    Prev
    Next
    INDEX
    Explanations

    finance, history, and specific domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     Atm
    1.50
     Vapor
    1.38
    Instance
    1.35
     actuation
    1.35
    apet
    1.32
     Fournier
    1.32
    8
    1.30
    ₁
    1.29
     Bautista
    1.29
    TAK
    1.28
    POSITIVE LOGITS
     rich
    1.59
     ricco
    1.52
    rich
    1.38
     Rich
    1.37
     envisaged
    1.36
     fished
    1.34
     clause
    1.33
    oxych
    1.32
     historians
    1.30
     relied
    1.30
    Activations Density 0.029%

    No Known Activations