© 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. 73208
    Prev
    Next
    INDEX
    Explanations

    the followed by abstract nouns

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

    The main thing this neuron does is detect numeric measurements (especially decimal or integer 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
    m
    -2.16
     what
    -1.97
    in
    -1.95
    ma
    -1.83
     Some
    -1.78
     when
    -1.76
     What
    -1.76
    id
    -1.73
    ang
    -1.73
    b
    -1.71
    POSITIVE LOGITS
     dalších
    2.38
     and
    2.02
    iliki
    1.77
     neumáticos
    1.77
    อื่น
    1.73
    libat
    1.73
    owm
    1.73
    
    1.68
    apj
    1.68
     möjlighet
    1.64
    Activations Density 0.239%

    No Known Activations