© 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. 40609
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation; names and context; specific phrases

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

    The main thing this neuron does is find numeric tokens (numbers and multi-digit figures).

    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
     that
    -1.78
     unbelievably
    -1.51
     افرادی
    -1.44
    糴
    -1.44
     žiad
    -1.43
     úpl
    -1.42
     flamboyant
    -1.42
     alluring
    -1.41
     😁
    -1.41
    槇
    -1.41
    POSITIVE LOGITS
     first
    2.09
     from
    1.91
     provide
    1.53
     give
    1.42
     '
    1.41
     brings
    1.40
     provides
    1.37
     serves
    1.37
     bring
    1.35
     helped
    1.34
    Activations Density 0.009%

    No Known Activations