© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21085
    Prev
    Next
    INDEX
    Explanations

    shortcut icon and generator meta

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

    This neuron detects HTML metadata elements (meta and link tags) in the document head that specify things like author, description, keywords, compatibility, icons, theme color, and other page-level metadata.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desmotiv
    -1.73
    
    -1.71
     masaje
    -1.68
    をご覧ください
    -1.63
    癭
    -1.59
     the
    -1.58
    の前に
    -1.55
     our
    -1.52
     rapidamente
    -1.48
     contribuir
    -1.47
    POSITIVE LOGITS
    6
    2.06
    8
    2.02
    .
    1.79
    7
    1.77
    4
    1.75
    2
    1.70
    z
    1.66
    3
    1.65
    ties
    1.62
    </em>
    1.59
    Activations Density 0.007%

    No Known Activations