© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 173188
    Prev
    Next
    INDEX
    Explanations

    light of, years ago, industry share, collecting quotes

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

    explaining comparisons and data patterns

    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
    ☮
    0.43
    讷
    0.43
    Ꮽ
    0.41
    న్య
    0.41
    פי
    0.40
    ന്തു
    0.40
    ุทธ
    0.40
    印度
    0.40
    proguard
    0.39
    囿
    0.38
    POSITIVE LOGITS
     с
    0.52
     bienes
    0.48
     ouvrages
    0.48
    rq
    0.48
    (){
    0.45
     ή
    0.44
     fillings
    0.44
     pericol
    0.44
     tấm
    0.44
     meubles
    0.44
    Activations Density 0.000%

    No Known Activations