© 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. 69557
    Prev
    Next
    INDEX
    Explanations

    supplier relationships

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

    serving models

    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
    شی
    0.49
    鄧
    0.49
     submitted
    0.47
    ومی
    0.46
     Decker
    0.45
    کان
    0.45
     ولی
    0.44
    کی
    0.44
    مت
    0.44
    კ
    0.44
    POSITIVE LOGITS
    exceptional
    0.61
    uir
    0.59
    aic
    0.52
    uq
    0.52
    ly
    0.52
    o
    0.52
    in
    0.51
    ar
    0.51
    oq
    0.51
    y
    0.50
    Activations Density 0.000%

    No Known Activations