© 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. 130199
    Prev
    Next
    INDEX
    Explanations

    fund theirStrip hardreported inoffer savings

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

    Boosting Machines

    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
    Negative Logits
     Privacy
    0.49
     warranties
    0.46
     spends
    0.45
    看出
    0.44
     machines
    0.44
     отличие
    0.44
     engineers
    0.43
    ቛ
    0.43
     Machines
    0.43
    端末
    0.43
    POSITIVE LOGITS
    ordination
    0.45
    imming
    0.43
    وید
    0.41
    elaide
    0.41
    μαν
    0.40
    ىڭ
    0.40
     DOE
    0.40
     STORM
    0.40
     نبود
    0.40
    ومان
    0.40
    Activations Density 0.002%

    No Known Activations