© 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. 59792
    Prev
    Next
    INDEX
    Explanations

    input/output levels and testing

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

    The neuron activates on numeric tokens and measurement values (e.g. “1.2 Vp-p,” “7.5 Ω,” “100 MHz,” etc.), so it’s detecting numeric specifications and units.

    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
    阻塞
    -0.82
    Bé
    -0.76
     electors
    -0.75
     Picard
    -0.74
    blica
    -0.73
     fuses
    -0.71
    onSelect
    -0.70
    璠
    -0.70
    タリー
    -0.69
    ﷲ
    -0.69
    POSITIVE LOGITS
    stest
    1.00
     tested
    0.94
    测
    0.92
    tested
    0.91
     Test
    0.86
    test
    0.85
     faſt
    0.85
    VECTOR
    0.84
    wrights
    0.83
     testing
    0.82
    Activations Density 0.004%

    No Known Activations