© 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. 83645
    Prev
    Next
    INDEX
    Explanations

    dumpster rental or trash disposal

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

    structured lists and headings

    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
    Smoothing
    0.49
    教室
    0.48
    oteric
    0.43
    房間
    0.43
    现在的
    0.42
     الأولى
    0.42
    ين
    0.42
    }&\
    0.41
    нача
    0.41
    青春
    0.41
    POSITIVE LOGITS
    sbParams
    0.47
     lube
    0.46
     animados
    0.44
     beş
    0.44
    パフォーマンス
    0.43
     основного
    0.43
     foothold
    0.43
    does
    0.43
    renderSquare
    0.43
     separado
    0.42
    Activations Density 0.001%

    No Known Activations