© 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. 66742
    Prev
    Next
    INDEX
    Explanations

    comparison of states or results

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

    The main thing this neuron does is find numeric tokens (quantities, measurements, and decimal values).

    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
    indicate
    -1.64
    tomorrow
    -1.63
    𓁹
    -1.62
    鵙
    -1.59
     indepen
    -1.55
     choisi
    -1.53
    yesterday
    -1.52
     باسلام
    -1.51
    🤯
    -1.50
     magie
    -1.47
    POSITIVE LOGITS
     from
    2.03
     perhaps
    1.86
     possibly
    1.82
     this
    1.77
     may
    1.76
     including
    1.75
     probably
    1.73
     which
    1.69
     encompassing
    1.66
     with
    1.66
    Activations Density 0.028%

    No Known Activations