© 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. 102157
    Prev
    Next
    INDEX
    Explanations

    swap out

    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
     They
    -1.73
     mereka
    -1.70
    ’?
    -1.61
    Their
    -1.59
     Também
    -1.42
    留意
    -1.41
     ‘
    -1.38
     Unfortunately
    -1.36
     The
    -1.34
    っちゃった
    -1.34
    POSITIVE LOGITS
    垍
    1.93
     the
    1.78
     maji
    1.60
    "
    1.59
    铪
    1.56
    赑
    1.49
    ?
    1.46
    }());
    1.46
     municipales
    1.45
     gogh
    1.44
    Activations Density 0.005%

    No Known Activations