© 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. 32920
    Prev
    Next
    INDEX
    Explanations

    Managers, visiting places

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

    distributed, available, and ongoing actions

    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
    Е
    0.54
    .
    0.51
    ١
    0.49
    Ա
    0.49
    Muj
    0.46
    Electronic
    0.46
     cierre
    0.45
    ਮ
    0.45
    كتور
    0.45
     participaron
    0.45
    POSITIVE LOGITS
    бавля
    0.49
    gdock
    0.48
    stava
    0.48
    гуу
    0.48
    वाने
    0.47
     संसा
    0.47
    ecer
    0.46
    erer
    0.46
    grou
    0.46
    言語
    0.46
    Activations Density 0.001%

    No Known Activations