© 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. 22-GEMMASCOPE-RES-131K
    7. 73210
    Prev
    Next
    INDEX
    Explanations

    either or

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

    The neuron strongly activates on numeric tokens (both integers and decimals), i.e. any standalone numbers or quantities 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_22/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
    觏
    -1.06
     then
    -1.05
    /
    -1.04
    <bos>
    -1.03
    だから
    -0.99
    åringen
    -0.97
     Empieza
    -0.96
     probably
    -0.96
     linf
    -0.94
    そして
    -0.94
    POSITIVE LOGITS
     other
    1.47
     equivalent
    1.41
     if
    1.35
     from
    1.29
     any
    1.27
     equivalents
    1.23
     другими
    1.20
     другим
    1.17
     else
    1.16
     других
    1.11
    Activations Density 0.045%

    No Known Activations