© 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. 212415
    Prev
    Next
    INDEX
    Explanations

    labor statistics

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

    decisions about spontaneous events

    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
     முன்னே
    0.55
     সতর্কতা
    0.53
    <unused667>
    0.53
    revalidator
    0.52
     விளை
    0.52
     বাণী
    0.50
     πάντα
    0.50
     rempl
    0.50
     seguro
    0.49
     أي
    0.48
    POSITIVE LOGITS
    k
    0.52
    第
    0.50
    麝
    0.48
    fier
    0.46
    2
    0.46
     mammalian
    0.46
    鈴木
    0.45
    ed
    0.44
    epam
    0.44
    zt
    0.43
    Activations Density 0.001%

    No Known Activations