© 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. 202568
    Prev
    Next
    INDEX
    Explanations

    find documents

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

    lack of agency

    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
    ogén
    0.47
     ít
    0.46
     ([[
    0.46
     воспользова
    0.46
    nál
    0.46
    ês
    0.45
    oomla
    0.45
     marít
    0.45
    ág
    0.45
    anych
    0.44
    POSITIVE LOGITS
    quote
    0.46
    嘿
    0.46
    embark
    0.46
     gak
    0.46
     leading
    0.44
    jacket
    0.44
    헉
    0.44
    えて
    0.43
    的说
    0.42
    super
    0.42
    Activations Density 0.000%

    No Known Activations