© 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. 147821
    Prev
    Next
    INDEX
    Explanations

    companies and countries

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

    emphasis markers

    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
    рия
    0.49
    erie
    0.43
    ム
    0.43
    :^(
    0.42
     découverte
    0.42
     від
    0.41
    う
    0.41
    די
    0.41
    ãi
    0.41
    ulasi
    0.41
    POSITIVE LOGITS
     erythrocytes
    0.59
    ittees
    0.52
     effluents
    0.52
     neutrophils
    0.51
     시간이
    0.51
     amphibians
    0.50
     energetics
    0.50
     chitosan
    0.49
    countries
    0.49
     Countries
    0.48
    Activations Density 0.002%

    No Known Activations