© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6658
    Prev
    Next
    INDEX
    Explanations

    Abstract

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

    The neuron selectively activates on numeric tokens containing decimal points (i.e., fractional numbers).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     to
    -1.80
    出して
    -1.50
    EUROPA
    -1.41
    釔
    -1.40
    }$
    -1.39
    HDD
    -1.38
     dezelfde
    -1.34
    合适的
    -1.33
    блица
    -1.30
    荃
    -1.30
    POSITIVE LOGITS
     $
    1.59
    逦
    1.58
    bebasan
    1.50
    的眼神
    1.49
    就要
    1.47
    買った
    1.42
     from
    1.41
    MÁS
    1.41
    龊
    1.39
    liśmy
    1.34
    Activations Density 0.002%

    No Known Activations