© 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. 149552
    Prev
    Next
    INDEX
    Explanations

    "the" followed by "protocol"

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

    API access, adulting, bills

    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
     and
    0.57
    ang
    0.54
    ↵
    0.50
    pick
    0.48
    and
    0.47
     strain
    0.46
    Wind
    0.46
     dissemination
    0.46
    terms
    0.45
     safety
    0.43
    POSITIVE LOGITS
    MZ
    0.52
    <unused11>
    0.51
    枤
    0.50
     ū
    0.49
     yuè
    0.49
    を受
    0.48
     esclusivamente
    0.48
     hMut
    0.48
    选举
    0.48
     upregulated
    0.47
    Activations Density 0.000%

    No Known Activations