© 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. 22-GEMMASCOPE-RES-131K
    7. 27997
    Prev
    Next
    INDEX
    Explanations

    code, punctuation, and specific words related to lists or properties

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

    The neuron selectively fires on numeric tokens (digits or number literals) in the text.

    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
    Gruß
    -1.14
    Grüße
    -1.12
    疴
    -1.11
     illustre
    -1.10
     delegado
    -1.10
    houette
    -1.05
    نجليزية
    -1.05
    Ār
    -1.05
     イラスト
    -1.04
    waarden
    -1.04
    POSITIVE LOGITS
    e
    0.97
    fang
    0.94
    3
    0.94
    4
    0.93
    m
    0.91
    DS
    0.91
    G
    0.91
     on
    0.90
    f
    0.90
    d
    0.90
    Activations Density 0.068%

    No Known Activations