© 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. 88825
    Prev
    Next
    INDEX
    Explanations

    business and organizational roles

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

    likely bile, on onion

    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
     উইল
    0.48
     детский
    0.48
    妵
    0.48
    тан
    0.47
     つ
    0.47
     театр
    0.47
    FDMA
    0.46
    Ⲡ
    0.46
     உற்பத்தி
    0.45
    าราง
    0.45
    POSITIVE LOGITS
    -
    0.47
    res
    0.46
     correr
    0.46
    (
    0.46
    ;
    0.45
     body
    0.45
    /
    0.44
     dit
    0.43
    meric
    0.43
     geen
    0.42
    Activations Density 0.001%

    No Known Activations