© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101485
    Prev
    Next
    INDEX
    Explanations

    direct effect

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

    This neuron detects tokens that are immediately paired with numerical measurements (i.e. words occurring alongside numeric values).

    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
     Bestimm
    -1.37
    {
    -1.34
    ون
    -1.21
    了一句
    -1.20
    OLA
    -1.17
     Borneo
    -1.16
     posse
    -1.16
    …
    -1.16
    </strong>
    -1.14
    vedades
    -1.13
    POSITIVE LOGITS
     direkte
    1.86
     direct
    1.83
    IRECT
    1.81
    direct
    1.70
     indirect
    1.62
    indirect
    1.60
     สำหรับ
    1.57
     bezpośred
    1.53
     مستقیم
    1.48
     Indirect
    1.47
    Activations Density 0.064%

    No Known Activations