© 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. 19112
    Prev
    Next
    INDEX
    Explanations

    code structures

    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
     our
    -2.11
     your
    -1.98
     about
    -1.60
     somebody
    -1.55
     always
    -1.47
     мы
    -1.47
     some
    -1.46
     plenty
    -1.40
    ara
    -1.33
     any
    -1.30
    POSITIVE LOGITS
     vanille
    1.59
     bourg
    1.49
    丏
    1.46
     industrie
    1.45
    eine
    1.45
     '-
    1.42
     剧照
    1.42
     canne
    1.41
     Après
    1.41
    rowser
    1.41
    Activations Density 0.062%

    No Known Activations