© 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. 19538
    Prev
    Next
    INDEX
    Explanations

    album charts

    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
    😲
    -1.55
     it
    -1.50
    😮
    -1.48
    cheinend
    -1.45
    🌚
    -1.38
    offering
    -1.32
    žité
    -1.32
    стоит
    -1.31
     firent
    -1.30
    🤯
    -1.30
    POSITIVE LOGITS
     also
    1.39
    ,”
    1.34
     our
    1.32
     on
    1.28
     today
    1.26
     supporting
    1.25
    ış
    1.25
     of
    1.24
     last
    1.24
     unbekannt
    1.23
    Activations Density 0.176%

    No Known Activations