© 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. 22-GEMMASCOPE-RES-131K
    4. 104272
    Prev
    Next
    INDEX
    Explanations

    other

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

    This neuron detects numeric tokens and numeric values (e.g., standalone numbers, percentages, or numeric constants).

    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
     篇
    -0.89
    ෘ
    -0.87
    iziert
    -0.85
     эти
    -0.85
    ethyl
    -0.83
     denen
    -0.82
    targets
    -0.81
    CONCLUSIONS
    -0.79
    toDouble
    -0.79
    悸
    -0.77
    POSITIVE LOGITS
     other
    1.27
     các
    1.21
     अन्य
    1.10
    supporting
    1.08
     supporting
    1.02
     surrounded
    0.97
     pozosta
    0.96
    hasMany
    0.94
    Other
    0.93
     innych
    0.90
    Activations Density 0.170%

    No Known Activations