© 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. 19672
    Prev
    Next
    INDEX
    Explanations

    continuous analog

    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
    ’
    -1.77
    B
    -1.60
    W
    -1.55
    8
    -1.55
    es
    -1.50
    M
    -1.46
    (
    -1.45
    am
    -1.43
    d
    -1.41
     few
    -1.40
    POSITIVE LOGITS
     でも
    1.68
     \&
    1.57
     moeili
    1.43
    繝
    1.39
     {
    1.38
    ΤΟ
    1.36
     yalnız
    1.34
     sonunda
    1.31
    jestel
    1.31
     उपलब्
    1.30
    Activations Density 0.051%

    No Known Activations