© 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. 66044
    Prev
    Next
    INDEX
    Explanations

    Java API class names

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

    The neuron activates on uppercase‐starting identifiers—i.e. class or type names—in code.

    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
     such
    -1.50
     each
    -1.21
     whether
    -1.17
     mitään
    -1.17
    包括
    -1.15
     [
    -1.10
     siitä
    -1.10
    不要
    -1.09
    chern
    -1.09
     the
    -1.08
    POSITIVE LOGITS
     conster
    1.31
     brune
    1.27
     ſou
    1.25
     ciment
    1.22
     liquide
    1.21
     anormal
    1.19
     brille
    1.18
     mondi
    1.17
     gide
    1.16
     colonie
    1.16
    Activations Density 0.007%

    No Known Activations