© 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. 223267
    Prev
    Next
    INDEX
    Explanations

    deal structure or retirement income

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

    character development

    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
    in
    0.45
    Iso
    0.44
    阅
    0.43
    ↵
    0.43
     hear
    0.43
     cyber
    0.42
    Wells
    0.42
    Downloading
    0.41
    FindAsync
    0.40
    Hear
    0.40
    POSITIVE LOGITS
     интерес
    0.56
    圃
    0.54
     институт
    0.52
     интересных
    0.52
    arta
    0.51
     выгод
    0.50
     spasms
    0.50
     مان
    0.47
     නිර්
    0.47
     intéressant
    0.47
    Activations Density 0.000%

    No Known Activations