© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9683
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. Nos

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

    The neuron fires whenever it sees a numeric value—especially decimal or measured quantities—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
     of
    -1.80
     also
    -1.70
    u
    -1.45
    an
    -1.31
    a
    -1.30
     only
    -1.27
     even
    -1.27
     but
    -1.17
    ay
    -1.16
    </em>
    -1.15
    POSITIVE LOGITS
     Перейти
    1.69
     sienten
    1.49
    isait
    1.49
    Britannique
    1.48
     değiştir
    1.45
     wahrscheinlich
    1.44
     initWithFrame
    1.41
    )—
    1.41
     yaşad
    1.39
    넋
    1.39
    Activations Density 0.020%

    No Known Activations