© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130808
    Prev
    Next
    INDEX
    Explanations

    code blocks or descriptions

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

    This neuron detects mentions of external library or framework identifiers (e.g. Guice, Guava, ModuleConfiguration) 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_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
     textView
    -1.45
     Onze
    -1.44
     bordados
    -1.43
    嵓
    -1.38
     eene
    -1.38
    liegende
    -1.38
    ὲ
    -1.37
     trattano
    -1.35
    lève
    -1.34
     lentejuelas
    -1.33
    POSITIVE LOGITS
     It
    1.68
     in
    1.50
     this
    1.28
     with
    1.27
     on
    1.23
     haciendo
    1.18
    之間
    1.13
     about
    1.12
     jego
    1.12
     his
    1.10
    Activations Density 0.006%

    No Known Activations