© 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. 184404
    Prev
    Next
    INDEX
    Explanations

    began firing, stop pushbutton

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

    how much effort

    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
    ”
    0.54
    RED
    0.52
     au
    0.50
     quitt
    0.50
     four
    0.48
     ecommerce
    0.47
     he
    0.47
     five
    0.46
     cinq
    0.46
     appoint
    0.46
    POSITIVE LOGITS
    ņas
    0.49
    isał
    0.47
     담
    0.46
    ҙ
    0.46
    atak
    0.46
     उपयोगी
    0.46
    adă
    0.45
     말씀
    0.45
     ஏற்படுத்த
    0.44
    zości
    0.43
    Activations Density 0.001%

    No Known Activations