© 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. 22-GEMMASCOPE-RES-131K
    7. 36243
    Prev
    Next
    INDEX
    Explanations

    identifying words

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

    This neuron fires on occurrences of the literal token “word” (and its plural “words”) in the text.

    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
    others
    -1.17
     aki
    -1.13
    вил
    -1.10
     afili
    -1.09
    ILogger
    -1.09
     Thé
    -1.06
     rojas
    -1.05
     for
    -1.05
    CastException
    -1.05
    ZONE
    -1.04
    POSITIVE LOGITS
     especially
    1.37
    adona
    1.32
     verheir
    1.29
     pensamiento
    1.24
     Especially
    1.23
     Erkrank
    1.22
     Mitarbeitern
    1.20
    譏
    1.16
     word
    1.15
     constituyen
    1.13
    Activations Density 0.039%

    No Known Activations