© 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. 90689
    Prev
    Next
    INDEX
    Explanations

    brand names or proper nouns

    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
    ar
    -2.88
    am
    -2.70
     is
    -2.48
    y
    -2.41
    ul
    -2.39
    ent
    -2.39
    ひた
    -2.36
    on
    -2.23
    in
    -2.20
    ane
    -2.20
    POSITIVE LOGITS
    There
    2.44
    ﹅
    2.27
    文化的
    2.27
    ühnen
    2.23
    暌
    2.23
     Gehalt
    2.22
    They
    2.22
     丼
    2.19
     şal
    2.14
    It
    2.13
    Activations Density 0.218%

    No Known Activations