© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16308
    Prev
    Next
    INDEX
    Explanations

    questions and locations

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

    This neuron activates on quantifying terms—e.g. words like “other” and standalone numerals.

    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
    וּ
    -1.41
    ֶּ
    -1.38
    ֶר
    -1.34
    ּוֹ
    -1.33
    ַּ
    -1.16
    ִּ
    -1.16
     policies
    -1.16
    ֵּ
    -1.15
    喁
    -1.13
     бампер
    -1.12
    POSITIVE LOGITS
     wondrous
    1.27
     religieux
    1.22
     sumptuous
    1.20
     gorgeous
    1.17
     ridiculously
    1.12
     luscious
    1.10
     horrid
    1.09
    了下去
    1.09
     opulent
    1.09
     famed
    1.06
    Activations Density 0.000%

    No Known Activations