© 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. 8919
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and symbols

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

    The neuron is detecting tokens that are numeric or number‐like (digit sequences, integers, decimals, etc.).

    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
     gedeelte
    -1.70
     láser
    -1.39
    欵
    -1.36
    Qs
    -1.33
    ":"",
    -1.32
     revient
    -1.31
     the
    -1.31
     wyposaż
    -1.30
     mischievous
    -1.28
     labores
    -1.27
    POSITIVE LOGITS
    daging
    1.40
    7
    1.25
    нов
    1.23
     ня
    1.22
    品です
    1.20
     It
    1.18
     ہے
    1.15
    ви
    1.15
     preghi
    1.13
    ījum
    1.11
    Activations Density 0.161%

    No Known Activations