© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10981
    Prev
    Next
    INDEX
    Explanations

    occasional or occasionally

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

    The neuron fires on occurrences of the word “occasional” (including the adverb form “occasionally”).

    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
    ᚔ
    -2.75
    糶
    -2.63
    秾
    -2.55
    ༷
    -2.53
    
    -2.48
     aqueles
    -2.45
     但
    -2.45
     aseguró
    -2.41
    皷
    -2.28
    ТУ
    -2.25
    POSITIVE LOGITS
    ↵
    3.41
    3
    2.95
    }
    2.91
    1
    2.63
    8
    2.61
    6
    2.61
     zulassen
    2.56
    7
    2.50
    性和
    2.50
    珎
    2.38
    Activations Density 0.004%

    No Known Activations