© 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. 34-GEMMASCOPE-RES-131K
    7. 78815
    Prev
    Next
    INDEX
    Explanations

    kotlin extensions OR psi

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

    This neuron fires on code‐namespace tokens—especially the keywords and dot separators in package/import paths.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ;
    -1.31
    ();
    -1.03
     [];
    -0.99
    êter
    -0.98
     imediatamente
    -0.98
    を抜
    -0.98
     "";
    -0.97
    ="">
    -0.94
     ruok
    -0.91
    ++;
    -0.90
    POSITIVE LOGITS
     to
    1.52
    extensions
    1.24
    kotlin
    1.23
     as
    1.16
     Kotlin
    1.09
     extensions
    1.05
     kotlin
    1.05
    Kotlin
    1.04
     extension
    1.03
    kot
    1.03
    Activations Density 0.023%

    No Known Activations