© 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. 10-GEMMASCOPE-RES-131K
    4. 29067
    Prev
    Next
    INDEX
    Explanations

    only

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

    The neuron fires on adverbs and function words that signal exclusivity or limitation (e.g. “only,” “solely,” “just”).

    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
    jäh
    -1.48
     også
    -1.41
    jährige
    -1.29
    schule
    -1.27
    jähriger
    -1.24
    OUGH
    -1.21
     également
    -1.21
    besondere
    -1.20
    beruf
    -1.19
    ก็
    -1.17
    POSITIVE LOGITS
    }
    1.59
    "
    1.55
     there
    1.49
     these
    1.48
     those
    1.42
    をはじめ
    1.34
     use
    1.30
    -
    1.30
     contará
    1.27
     possesses
    1.25
    Activations Density 0.065%

    No Known Activations