© 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. 34-GEMMASCOPE-RES-131K
    7. 82778
    Prev
    Next
    INDEX
    Explanations

    code, data, text handling

    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_34/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
    Values
    -0.87
    捺
    -0.87
    ❞
    -0.85
    Eyes
    -0.84
    ''');
    -0.82
    ёз
    -0.81
     vetorial
    -0.81
     судеб
    -0.81
    dagogik
    -0.81
    stoj
    -0.80
    POSITIVE LOGITS
     還
    0.83
     还
    0.81
    WindowListener
    0.77
    摻
    0.77
    となりました
    0.74
    Lí
    0.73
    )
    0.71
     monsoon
    0.71
     newline
    0.71
     holog
    0.69
    Activations Density 0.011%

    No Known Activations