© 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. 10-GEMMASCOPE-RES-131K
    7. 8233
    Prev
    Next
    INDEX
    Explanations

    quantities and units

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

    The neuron spikes on numeric tokens (sequences of digits), i.e. when it encounters 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
     giving
    -1.88
     make
    -1.84
     as
    -1.82
     your
    -1.80
     making
    -1.72
     on
    -1.70
     makes
    -1.69
     people
    -1.68
     taking
    -1.67
     give
    -1.66
    POSITIVE LOGITS
     diamant
    1.86
     pittores
    1.75
     tirs
    1.73
     baden
    1.73
     rente
    1.70
     tille
    1.69
     perle
    1.63
     geograf
    1.63
     spesial
    1.61
     nabi
    1.59
    Activations Density 0.046%

    No Known Activations