© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77611
    Prev
    Next
    INDEX
    Explanations

    loading shared libraries

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

    This neuron activates on low-level C code syntax—particularly on identifiers, operators, and punctuation involved in function-pointer declarations and dynamic symbol lookups.

    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
    Attend
    -0.73
    gering
    -0.73
    तीय
    -0.72
     הכל
    -0.71
    狗
    -0.70
     attended
    -0.70
    Legendary
    -0.69
     gratuitamente
    -0.69
    чу
    -0.69
     perten
    -0.68
    POSITIVE LOGITS
     loading
    1.39
     Loading
    1.24
     unload
    1.21
     loader
    1.20
     Load
    1.19
     load
    1.19
    Unload
    1.19
    symbols
    1.13
    Loading
    1.12
     symbols
    1.11
    Activations Density 0.109%

    No Known Activations