© 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. 194533
    Prev
    Next
    INDEX
    Explanations

    non-bearing, winning, or money

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

    reasons or purpose for outcomes

    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
     parochial
    0.50
     захід
    0.50
    politics
    0.48
    cheidung
    0.48
     பழைய
    0.47
    కీయ
    0.47
    쫒
    0.47
     Архи
    0.47
     полицей
    0.46
    urrection
    0.46
    POSITIVE LOGITS
     ami
    0.52
     nell
    0.48
     marco
    0.48
     independently
    0.46
     riêng
    0.45
    RESULTS
    0.44
    ℙ
    0.44
     L
    0.44
     separately
    0.43
     dea
    0.43
    Activations Density 0.000%

    No Known Activations