© 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. 14862
    Prev
    Next
    INDEX
    Explanations

    names and locations like Bordeaux

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

    The neuron detects capitalized identifiers or proper names (i.e. named entities).

    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
    л
    -3.31
    “
    -2.97
     breite
    -2.92
     heutige
    -2.69
     genaue
    -2.59
     \_
    -2.58
    vignon
    -2.53
     zweite
    -2.53
     komplette
    -2.53
     ficar
    -2.52
    POSITIVE LOGITS
    葙
    2.88
    ཋ
    2.72
     honom
    2.58
    ープン
    2.53
    ânsito
    2.45
    釭
    2.42
    ي
    2.39
     всѣ
    2.39
     analogous
    2.31
     توسط
    2.30
    Activations Density 0.003%

    No Known Activations