© 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. 49578
    Prev
    Next
    INDEX
    Explanations

    constant restrict

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

    The neuron is strongly triggered by C/C++ type declarations—particularly type keywords (like char, const, unsigned) and pointer symbols (*) in function signatures.

    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
     ilustraciones
    -0.82
     béton
    -0.78
     Tuf
    -0.75
     Burner
    -0.73
    Ран
    -0.73
    SaveChangesAsync
    -0.72
     ANNEX
    -0.72
    
    -0.71
    nader
    -0.71
    ウザ
    -0.71
    POSITIVE LOGITS
    restrict
    1.68
     restrict
    1.33
    const
    1.24
    RESTRICT
    1.22
     const
    1.11
    Const
    1.06
     RESTRICT
    0.97
     vanligt
    0.94
    pont
    0.91
     Const
    0.90
    Activations Density 0.030%

    No Known Activations