© 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. 31720
    Prev
    Next
    INDEX
    Explanations

    quotation marks followed by semicolon

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

    closing mathematical expressions

    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
    0
    0.91
    2
    0.88
    3
    0.83
    ς
    0.81
    4
    0.78
    otho
    0.75
    0.75
    hok
    0.74
    5
    0.73
    hara
    0.72
    POSITIVE LOGITS
    ี
    0.77
     เ
    0.72
     โ
    0.68
    로
    0.67
     can
    0.66
    し
    0.66
     sides
    0.61
    ุด
    0.61
     wolf
    0.60
    .。
    0.60
    Activations Density 0.001%

    No Known Activations