© 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. 67625
    Prev
    Next
    INDEX
    Explanations

    as a function of

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

    The neuron activates on numeric tokens (measurements or quantities), i.e. on numbers and numerical values 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
     exceptionally
    -2.14
     !!!!!
    -2.09
     unending
    -2.05
     frontières
    -2.03
     sooo
    -2.00
    !!!!!!!!!
    -2.00
     dépenses
    -2.00
     !!!!
    -1.98
     Provides
    -1.98
     soooo
    -1.96
    POSITIVE LOGITS
     what
    2.61
     two
    2.44
     three
    2.42
     using
    2.36
     one
    2.36
     four
    2.28
     our
    2.22
     putting
    2.20
     by
    2.14
     their
    2.13
    Activations Density 0.025%

    No Known Activations