© 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. 13141
    Prev
    Next
    INDEX
    Explanations

    numbers from 0 to 100

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

    The neuron fires on numeric tokens (digit sequences, including standalone numbers or numbers with hyphens), i.e. it detects numbers 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_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
     and
    -1.84
     is
    -1.66
    ThemeOverlay
    -1.44
     tři
    -1.34
    ('');
    -1.31
     commonplace
    -1.29
    }
    -1.27
    riages
    -1.27
    âche
    -1.27
    سطس
    -1.27
    POSITIVE LOGITS
     will
    1.60
     are
    1.58
    鞏
    1.51
     this
    1.39
     "..\..\..\
    1.36
     not
    1.32
    rceil
    1.30
     erinner
    1.27
    خل
    1.26
     cilvē
    1.23
    Activations Density 0.031%

    No Known Activations