© 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. 87109
    Prev
    Next
    INDEX
    Explanations

    paths and filenames

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

    The neuron fires on numeric tokens (integer or floating‐point constants) appearing in code or command lines.

    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
     dictionnaire
    -1.31
    gegevens
    -1.23
     if
    -1.18
     visuelle
    -1.16
     “
    -1.15
     ideen
    -1.13
     throughout
    -1.12
     stammen
    -1.09
     beurre
    -1.06
    =("
    -1.06
    POSITIVE LOGITS
    mme
    1.39
    ícias
    1.36
     ۸
    1.33
    ඍ
    1.27
    ophosph
    1.24
     ferocious
    1.23
    謳
    1.23
     consequent
    1.23
    孩子的
    1.21
     ucapnya
    1.21
    Activations Density 0.209%

    No Known Activations