© 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. 10-GEMMASCOPE-RES-131K
    7. 119529
    Prev
    Next
    INDEX
    Explanations

    words starting with char

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

    The neuron fires on occurrences of the letter sequence “char,” whether standalone or as part of larger 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_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
    泂
    -2.97
    涷
    -2.80
    ↵
    -2.70
     είναι
    -2.67
    ଢ
    -2.66
     chega
    -2.63
    
    -2.50
     pertenec
    -2.50
    嗩
    -2.38
    ientras
    -2.36
    POSITIVE LOGITS
    しちゃ
    2.41
    豨
    2.39
     –
    2.34
    でしたが
    2.28
    ありますが
    2.25
    ⭏
    2.20
    霂
    2.19
    ﾛ
    2.09
    鯓
    2.08
    شك
    2.00
    Activations Density 0.006%

    No Known Activations