© 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. 136128
    Prev
    Next
    INDEX
    Explanations

    strategic decision-making

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

    smallest, size, purpose, term

    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
    Madison
    0.43
    rma
    0.43
    olle
    0.40
    ﾟ
    0.40
    ಷ್ಣ
    0.39
    Aliases
    0.39
    sail
    0.38
    0
    0.38
    လ
    0.38
     masts
    0.38
    POSITIVE LOGITS
    互動
    0.51
     propio
    0.50
    についても
    0.49
     comportamento
    0.49
     poorer
    0.48
     இந்தியா
    0.47
     sinc
    0.47
     PDE
    0.47
    噙
    0.47
    نسب
    0.46
    Activations Density 0.001%

    No Known Activations