© 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. 10-GEMMASCOPE-RES-131K
    7. 42608
    Prev
    Next
    INDEX
    Explanations

    trials and repetitions

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

    The neuron detects numeric tokens—whether counts or measured values—throughout the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    chnung
    -1.85
    銮
    -1.76
    //};
    -1.72
    }
    -1.64
    ivät
    -1.63
     проблему
    -1.58
    之时
    -1.57
    濑
    -1.57
    玥
    -1.55
     ihrem
    -1.54
    POSITIVE LOGITS
    (
    2.39
    )
    2.00
     '
    1.98
    牁
    1.92
    $
    1.91
     Its
    1.88
    Its
    1.85
    淠
    1.78
    its
    1.77
     gewin
    1.63
    Activations Density 0.009%

    No Known Activations