© 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. 2722
    Prev
    Next
    INDEX
    Explanations

    format descriptions

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

    specifying output format

    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
     in
    1.22
     equation
    0.94
    </h2>
    0.87
     equations
    0.87
    DE
    0.83
    t
    0.82
    는
    0.76
    </b>
    0.75
    ים
    0.75
    b
    0.74
    POSITIVE LOGITS
     फॉर्मेट
    1.00
     formatos
    0.98
    格式
    0.97
     Format
    0.94
     формат
    0.89
    Format
    0.86
     FORMAT
    0.84
    Formatting
    0.82
     प्रारूप
    0.79
    formats
    0.79
    Activations Density 0.006%

    No Known Activations