© 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. 22-GEMMASCOPE-RES-131K
    7. 16296
    Prev
    Next
    INDEX
    Explanations

    URLs and foreign terms

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

    The neuron fires most strongly on standalone Wikipedia‐style titles or section headings (e.g. “External links,” “References,” film titles, meta‐analysis headings, taxobox entries).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    blest
    -0.87
    bux
    -0.85
     aldea
    -0.84
    "],
    -0.84
    mehr
    -0.83
     Brasileiro
    -0.83
     большинстве
    -0.81
    🎧
    -0.80
     wielu
    -0.80
     hebat
    -0.79
    POSITIVE LOGITS
    Portály
    1.24
    ไม่มี
    1.07
     unknown
    0.93
    か月
    0.88
     obscurity
    0.84
    ัย
    0.82
     Balkans
    0.82
     nobody
    0.82
    暂无
    0.81
     presumably
    0.81
    Activations Density 0.258%

    No Known Activations