© 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. 74954
    Prev
    Next
    INDEX
    Explanations

    implies mathematical statements

    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
     Novembre
    -1.76
    派的
    -1.76
     ворота
    -1.75
     the
    -1.71
    ',
    -1.67
     iLocal
    -1.66
     télécharger
    -1.63
    кож
    -1.63
    Также
    -1.61
     ſuch
    -1.59
    POSITIVE LOGITS
     is
    2.42
     would
    1.91
    但却
    1.88
     they
    1.85
     when
    1.84
     estratégica
    1.80
    botella
    1.78
     portátil
    1.77
     cromado
    1.73
    取决
    1.71
    Activations Density 0.025%

    No Known Activations