© 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. 19618
    Prev
    Next
    INDEX
    Explanations

    // code comments

    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
    p
    -1.71
     of
    -1.70
    j
    -1.44
     vectorielles
    -1.41
    しまいます
    -1.29
     torino
    -1.25
    r
    -1.24
     crushes
    -1.24
     mineures
    -1.23
     наверное
    -1.20
    POSITIVE LOGITS
     but
    1.81
     it
    1.66
     collaborazione
    1.52
    歃
    1.50
     На
    1.41
    🪆
    1.35
    🦣
    1.33
    ᛬
    1.27
    .."
    1.27
     espiral
    1.23
    Activations Density 0.748%

    No Known Activations