© 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. 66376
    Prev
    Next
    INDEX
    Explanations

    start of code or lists

    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
     Although
    -1.06
     for
    -1.02
     over
    -0.97
     by
    -0.93
     provided
    -0.91
     from
    -0.90
     During
    -0.90
     Though
    -0.90
     in
    -0.89
     However
    -0.89
    POSITIVE LOGITS
    靂
    1.00
     bloques
    0.98
    鶿
    0.91
     चीज़
    0.89
    िज
    0.88
     FOCUS
    0.86
     ответа
    0.86
     accentu
    0.85
     ハー
    0.85
    llac
    0.85
    Activations Density 0.000%

    No Known Activations