© 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. 129559
    Prev
    Next
    INDEX
    Explanations

    math array matrices

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

    This neuron fires on numeric tokens that include a decimal point (i.e. floating-point numbers).

    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
    One
    -2.20
    Because
    -2.03
     invigor
    -2.00
     Unlike
    -1.98
     from
    -1.97
    Despite
    -1.96
     Although
    -1.96
    Since
    -1.95
    Unlike
    -1.92
    Several
    -1.90
    POSITIVE LOGITS
     decidedly
    2.19
    during
    2.19
     overly
    2.08
    within
    2.05
    without
    2.00
     predominantly
    1.98
     sooo
    1.91
     extremely
    1.91
     praticamente
    1.89
     vastly
    1.87
    Activations Density 0.001%

    No Known Activations