© 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. 247391
    Prev
    Next
    INDEX
    Explanations

    shortcode

    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
     儿童
    0.49
    >∕
    0.47
     polymer
    0.45
    marine
    0.45
    ૂર્ણ
    0.45
    polymer
    0.45
     بندی
    0.43
    uld
    0.43
     জলে
    0.42
     ভগবান
    0.42
    POSITIVE LOGITS
    водства
    0.50
    дій
    0.49
    amax
    0.46
    ?
    0.45
    ья
    0.45
    ίκ
    0.45
    凸
    0.44
     Wem
    0.44
    TrackedDevice
    0.43
     Vittorio
    0.43
    Activations Density 0.000%

    No Known Activations