© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65683
    Prev
    Next
    INDEX
    Explanations

    plural nouns denoting categories

    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
     from
    -2.16
     because
    -1.92
     and
    -1.91
     where
    -1.77
     with
    -1.48
     jeho
    -1.39
     who
    -1.38
     at
    -1.35
    více
    -1.34
     bahkan
    -1.34
    POSITIVE LOGITS
     некоторых
    1.54
    两种
    1.52
    Gibt
    1.36
    两只
    1.35
     are
    1.32
    如果有
    1.25
    iség
    1.25
     resultant
    1.25
    o
    1.24
    9
    1.23
    Activations Density 0.136%

    No Known Activations