© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105861
    Prev
    Next
    INDEX
    Explanations

    entity names followed by punctuation

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

    The neuron fires strongly on tokens that are part of proper names or branded identifiers (e.g. author names, package or organization 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_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
    
    -1.25
     dunkel
    -1.24
    ्टर
    -1.23
    ·
    -1.23
     etui
    -1.22
     trám
    -1.22
    :''
    -1.20
     mors
    -1.20
     kuns
    -1.20
     Ukra
    -1.18
    POSITIVE LOGITS
     it
    1.63
     they
    1.42
     selben
    1.40
     It
    1.39
     that
    1.31
     even
    1.23
     in
    1.21
     bleek
    1.20
     même
    1.17
     see
    1.16
    Activations Density 0.192%

    No Known Activations