© 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. 184871
    Prev
    Next
    INDEX
    Explanations

    business and trade

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

    where to start accessing facilities

    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
     váy
    0.49
     écrire
    0.48
    ()];
    0.46
     aggi
    0.46
     Uso
    0.46
     появления
    0.44
     Diy
    0.44
     ameri
    0.44
     esophageal
    0.44
     abbrevi
    0.44
    POSITIVE LOGITS
    nta
    0.50
    勸
    0.49
    trading
    0.48
    TRADE
    0.47
     trading
    0.47
    detail
    0.46
     trade
    0.46
    ITIES
    0.45
    TIT
    0.45
    details
    0.45
    Activations Density 0.000%

    No Known Activations