© 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. 106590
    Prev
    Next
    INDEX
    Explanations

    capabilities are or Tehran holidays

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

    figure, kitchen, hours, picnic, even

    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
     coconut
    0.47
    霁
    0.47
    감이
    0.47
    िपल
    0.46
     자동으로
    0.46
    ることが
    0.46
    िती
    0.46
    ิทธิภาพ
    0.46
     Merrick
    0.45
     otomatik
    0.44
    POSITIVE LOGITS
    ap
    0.57
    mp
    0.54
    chio
    0.51
    hel
    0.50
    a
    0.49
    ca
    0.47
    ga
    0.47
    hello
    0.47
    an
    0.46
    i
    0.46
    Activations Density 0.000%

    No Known Activations