© 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. 45135
    Prev
    Next
    INDEX
    Explanations

    HTML tags and formatting

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

    XML/HTML metadata fields

    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
            
    0.48
    <0x0D>
    0.48
     \
    0.48
     a
    0.48
    摘要
    0.46
     `
    0.45
                    
    0.45
     Hard
    0.43
    \
    0.43
     Prometheus
    0.43
    POSITIVE LOGITS
    >≤</
    0.61
    >/</
    0.49
    >→</
    0.49
     inglesa
    0.48
    >:</
    0.48
    ណ៍
    0.47
     galima
    0.46
    ><%=
    0.46
    ージ
    0.45
     vitth
    0.45
    Activations Density 0.000%

    No Known Activations