© 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. 22-GEMMASCOPE-RES-131K
    4. 95544
    Prev
    Next
    INDEX
    Explanations

    names and foreign words

    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_22/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
    -1.55
     long
    -1.50
     for
    -1.44
     all
    -1.37
     just
    -1.32
     so
    -1.27
     since
    -1.25
     Get
    -1.20
     because
    -1.20
     system
    -1.18
    POSITIVE LOGITS
    ご覧
    1.56
     ciertos
    1.47
     ciertas
    1.43
     alcuni
    1.41
    ご覧ください
    1.36
     idiotic
    1.31
     nabíz
    1.30
     カジュアル
    1.27
     ナイロン
    1.27
     procesamiento
    1.26
    Activations Density 0.001%

    No Known Activations