© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7305
    Prev
    Next
    INDEX
    Explanations

    C/C++ stdlib programming code

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

    The neuron fires on C/C++ code keywords and identifiers (e.g. “C,” “struct,” “typedef,” “char,” constructors/destructors) indicating a code snippet in that language.

    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
     the
    -1.14
     entschieden
    -1.13
     zurückge
    -1.09
     sobą
    -1.04
     bevorzug
    -1.03
     aktuellen
    -1.03
     schweren
    -1.02
     vermutlich
    -1.02
     offensichtlich
    -1.01
     that
    -1.00
    POSITIVE LOGITS
    "",
    
    1.28
     and
    1.25
     вона
    1.20
    헙
    1.12
    Какие
    1.10
     знаете
    1.07
     familiale
    1.06
     correcte
    1.06
    нял
    1.06
     Init
    1.05
    Activations Density 0.514%

    No Known Activations