© 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. 102608
    Prev
    Next
    INDEX
    Explanations

    numbers close to 100%

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

    The neuron detects numeric tokens representing decimal numbers or percentages (e.g. “99.9,” “9.9%,” “35.25”).

    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
     are
    -1.88
     seem
    -1.84
     was
    -1.78
     Our
    -1.71
     then
    -1.70
    栳
    -1.70
     škoda
    -1.52
     come
    -1.52
     actualiza
    -1.50
     have
    -1.48
    POSITIVE LOGITS
    ftrag
    1.61
     Universite
    1.52
    medriver
    1.48
     laſt
    1.45
    よー
    1.42
     Atlan
    1.40
     firft
    1.40
     magi
    1.38
    VARCHAR
    1.38
     diamante
    1.38
    Activations Density 0.012%

    No Known Activations