© 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. 195093
    Prev
    Next
    INDEX
    Explanations

    area suited for customers

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

    computational errors or divisibility

    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
    БА
    0.48
     politica
    0.46
    Кла
    0.45
    1
    0.45
     caso
    0.44
     besonderen
    0.44
    О
    0.44
    Ба
    0.43
    Caso
    0.43
    Ком
    0.43
    POSITIVE LOGITS
     माध्य
    0.52
    ancel
    0.48
    subsetneq
    0.46
    缜
    0.46
     염
    0.46
     훨씬
    0.46
    indexing
    0.45
    tois
    0.44
     बेहतरीन
    0.43
     Schles
    0.42
    Activations Density 0.000%

    No Known Activations