© 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. 132910
    Prev
    Next
    INDEX
    Explanations

    easy to use

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

    pasting examples or instructions

    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
     toothbrush
    0.48
     landlords
    0.46
    兒童
    0.46
    employee
    0.45
     Corral
    0.45
    ليا
    0.44
     carrots
    0.43
    ي
    0.43
    лами
    0.42
     employee
    0.42
    POSITIVE LOGITS
     mockery
    0.49
     qnt
    0.46
     سین
    0.43
    ibhav
    0.43
    bih
    0.43
     afar
    0.43
    พลิ
    0.42
     šť
    0.42
     मध्य
    0.41
     uproar
    0.41
    Activations Density 0.000%

    No Known Activations