© 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. 22-GEMMASCOPE-RES-131K
    7. 40258
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming constructs

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

    The neuron detects numeric literals (integers) 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_22/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
    Vä
    -1.12
    dä
    -1.04
    rijf
    -0.91
    bundet
    -0.91
    йна
    -0.89
     virker
    -0.86
    Criter
    -0.85
     entrando
    -0.85
     limpa
    -0.85
    änk
    -0.84
    POSITIVE LOGITS
     where
    1.02
     except
    1.00
     including
    0.99
     what
    0.94
    에서는
    0.92
    ↩
    0.90
     with
    0.90
     those
    0.87
    ಠ
    0.87
    pae
    0.85
    Activations Density 0.013%

    No Known Activations