© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93192
    Prev
    Next
    INDEX
    Explanations

    fictional characters and places

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

    The main thing this neuron does is find and highlight proper names (named entities), especially distinctive person or place names.

    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
     uwe
    -1.22
     dieß
    -1.20
     Jego
    -1.20
    莇
    -1.19
     geograf
    -1.17
     見える
    -1.13
    featuring
    -1.13
     ambassade
    -1.10
     attivo
    -1.10
     gebra
    -1.09
    POSITIVE LOGITS
     from
    1.16
     почти
    1.05
    ından
    1.03
     volver
    0.95
    çade
    0.92
     in
    0.92
     Stufen
    0.92
     पूरी
    0.91
     ((
    0.90
     только
    0.90
    Activations Density 0.052%

    No Known Activations