© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40676
    Prev
    Next
    INDEX
    Explanations

    IEEE wireless standards

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

    The main thing this neuron does is detect numeric measurements (especially floating‐point values) often paired with technical units (e.g., frequencies, data rates, or hardware specs).

    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
    </u>
    -1.74
    也是
    -1.41
    _
    -1.41
    </h4>
    -1.39
    ();
    -1.38
     meinte
    -1.36
    结语
    -1.35
    由于
    -1.34
     cias
    -1.33
     some
    -1.31
    POSITIVE LOGITS
     éstos
    1.26
     kulinar
    1.25
     decimos
    1.20
    抟
    1.20
     declaró
    1.19
     llego
    1.19
    给我们
    1.18
     Weitere
    1.17
     discer
    1.16
     llegan
    1.16
    Activations Density 0.029%

    No Known Activations