© 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. 68973
    Prev
    Next
    INDEX
    Explanations

    semantic features

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

    The neuron responds to high‐frequency function words (like “is,” “that,” “but,” “you,” “to,” etc.)—including their equivalents in Indonesian—i.e. grammatical “stop” words.

    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
    תודה
    -1.43
     cortinas
    -1.27
    Tahun
    -1.26
    敍
    -1.23
     sesiones
    -1.23
    していました
    -1.23
    tranh
    -1.21
    쎄
    -1.20
    Karakteristik
    -1.20
    אין
    -1.20
    POSITIVE LOGITS
     “
    1.44
     also
    1.32
    ER
    1.29
    H
    1.20
     
    1.19
     .
    1.18
    THE
    1.14
    на
    1.14
      
    1.12
     is
    1.11
    Activations Density 0.001%

    No Known Activations