© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84078
    Prev
    Next
    INDEX
    Explanations

    comparison values and ratios

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

    The neuron activates on numeric tokens and measurement-related numbers (digits, ratios, exponents, units, and similar numeric entries).

    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
     percentages
    -0.92
    Percentage
    -0.91
     percentage
    -0.90
     Percentage
    -0.82
    percentage
    -0.79
     amount
    -0.78
     such
    -0.73
    ным
    -0.69
    tigungs
    -0.69
    第
    -0.69
    POSITIVE LOGITS
     unity
    2.05
    unity
    1.59
     Unity
    1.54
    Unity
    1.48
     UNITY
    1.34
    UNITY
    1.20
     unidad
    1.02
     unité
    1.02
     value
    1.01
    値
    0.94
    Activations Density 0.070%

    No Known Activations