© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117199
    Prev
    Next
    INDEX
    Explanations

    programming library components

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

    The neuron strongly activates on tokens that are numeric (digits or number sequences), 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_34/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
     tombs
    -0.73
    書の
    -0.67
     Sonora
    -0.66
    贬
    -0.65
    kola
    -0.65
     Ах
    -0.65
    Gpu
    -0.64
    izio
    -0.64
     neuroscience
    -0.63
    attr
    -0.63
    POSITIVE LOGITS
    usable
    0.79
     nang
    0.79
     INDUSTRIAL
    0.73
    loyee
    0.69
     usable
    0.69
    Cubit
    0.67
    opinion
    0.66
     sitting
    0.65
    lecular
    0.64
    鶴
    0.64
    Activations Density 0.063%

    No Known Activations