© 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. 34-GEMMASCOPE-RES-131K
    7. 38017
    Prev
    Next
    INDEX
    Explanations

    natural areas and support

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

    The neuron fires on numeric tokens expressing quantities, measurements, or counts (e.g. hectares, percentages, and large numbers).

    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
    Стан
    -1.09
    آم
    -0.97
    startActivity
    -0.95
     будет
    -0.91
    ETRY
    -0.88
     pamamagitan
    -0.88
    pref
    -0.87
     different
    -0.86
    地点
    -0.85
     affitto
    -0.84
    POSITIVE LOGITS
     supports
    1.89
    supporting
    1.67
     supporting
    1.63
    supports
    1.61
    Supporting
    1.53
     support
    1.53
     Supports
    1.53
    Supports
    1.52
    SUPPORT
    1.32
     SUPPORT
    1.27
    Activations Density 0.053%

    No Known Activations