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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65672
    Prev
    Next
    INDEX
    Explanations

    occasional or occasionally

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

    The neuron fires strongly on adverbs and adjectives that denote infrequency (e.g. “occasional,” “occasionally,” “rarely”).

    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
     opérateur
    -2.08
    ᚔ
    -1.82
     یا
    -1.78
     desglose
    -1.78
     defied
    -1.76
    ჻
    -1.76
    嚭
    -1.75
    iculous
    -1.75
     Infór
    -1.74
    絝
    -1.73
    POSITIVE LOGITS
    n
    2.05
    }
    2.03
     but
    1.80
    k
    1.80
    b
    1.80
    d
    1.77
     gets
    1.76
    r
    1.74
     „
    1.71
    ’
    1.70
    Activations Density 0.011%

    No Known Activations