© 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. 98603
    Prev
    Next
    INDEX
    Explanations

    code if statements

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

    The neuron activates on numeric literal tokens (integer or floating‐point constants) 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
     that
    -1.33
    jší
    -1.08
    (!__
    -1.06
     who
    -0.98
    лександр
    -0.98
     Kč
    -0.96
     déput
    -0.95
     znal
    -0.93
     """",
    -0.92
     whose
    -0.91
    POSITIVE LOGITS
    varande
    0.89
    越來越
    0.88
    幸运
    0.88
    优点
    0.85
     adjoining
    0.82
    改为
    0.81
    剧本
    0.80
    決め
    0.80
    最初に
    0.80
     instead
    0.79
    Activations Density 0.001%

    No Known Activations