© 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. 21139
    Prev
    Next
    INDEX
    Explanations

    java import statements

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

    The neuron fires on numeric tokens (especially version numbers or other decimal literals) in import or package statements.

    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
    ⚌
    -1.44
    鸲
    -1.35
     начин
    -1.34
    缯
    -1.34
    すぎて
    -1.32
    讠
    -1.32
    ⇴
    -1.31
     három
    -1.31
     dissatisfaction
    -1.30
     assurent
    -1.30
    POSITIVE LOGITS
     some
    1.85
     one
    1.79
     new
    1.59
     on
    1.55
     however
    1.41
    Some
    1.37
     this
    1.33
     going
    1.31
     two
    1.30
     should
    1.27
    Activations Density 0.003%

    No Known Activations