© 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. 47502
    Prev
    Next
    INDEX
    Explanations

    constants and names

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

    The neuron strongly activates on programming‐language syntax markers—like semicolons, keywords (public, class, static, final), and comment tokens—in source 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_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
     aéreo
    -0.94
    studios
    -0.79
     instead
    -0.76
     tecnológico
    -0.76
     pertinentes
    -0.75
     dachte
    -0.75
    ロゴ
    -0.73
    点を
    -0.73
     matemáticas
    -0.73
     hairst
    -0.72
    POSITIVE LOGITS
     constants
    1.91
    constant
    1.46
     names
    1.46
     constant
    1.44
     Constant
    1.34
    Constant
    1.34
     Constants
    1.34
     CONSTANT
    1.33
    constants
    1.32
     constante
    1.30
    Activations Density 0.025%

    No Known Activations