© 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. 34-GEMMASCOPE-RES-131K
    7. 94072
    Prev
    Next
    INDEX
    Explanations

    starting of phrases

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

    This neuron detects numeric tokens, especially multi‐digit numbers such as dates and counts.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Bete
    -0.73
    !\!\
    -0.72
    lenme
    -0.72
    áska
    -0.71
    厦
    -0.69
    がある
    -0.67
     nadat
    -0.66
    theria
    -0.65
     Mercer
    -0.63
     escritor
    -0.62
    POSITIVE LOGITS
     Mathieu
    0.84
    bustion
    0.83
     oficina
    0.78
    nok
    0.78
    サミ
    0.75
    ibatkan
    0.74
    Jor
    0.74
    FontOfSize
    0.74
    rines
    0.74
     countryside
    0.73
    Activations Density 0.020%

    No Known Activations