© 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. 10-GEMMASCOPE-RES-131K
    7. 112649
    Prev
    Next
    INDEX
    Explanations

    identifying "one of"

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

    The neuron is primarily activated by numeric tokens (numbers, including counts and measurements) in the text.

    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
     テープ
    -1.79
    那麼
    -1.59
     havaianas
    -1.57
     incredi
    -1.45
     diferite
    -1.44
     allerlei
    -1.43
    ↵↵
    -1.43
     verschillende
    -1.42
     nori
    -1.41
     nostal
    -1.40
    POSITIVE LOGITS
     when
    1.75
     still
    1.60
     not
    1.57
    ètres
    1.55
     because
    1.52
     on
    1.52
    krát
    1.49
    These
    1.48
     cuz
    1.48
     ....
    1.47
    Activations Density 0.019%

    No Known Activations