© 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. 1361
    Prev
    Next
    INDEX
    Explanations

    mathematical division and expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     (
    -2.16
     to
    -1.88
     should
    -1.72
     will
    -1.69
    </td>
    -1.65
     like
    -1.64
     but
    -1.63
     in
    -1.59
     the
    -1.52
     "
    -1.47
    POSITIVE LOGITS
    こともあります
    1.63
    tså
    1.56
     itinéraire
    1.51
     esimerkiksi
    1.51
    schirm
    1.50
     personlig
    1.48
     morceau
    1.48
     türkiye
    1.47
     arrêter
    1.45
    también
    1.43
    Activations Density 0.292%

    No Known Activations