© 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. 47641
    Prev
    Next
    INDEX
    Explanations

    designer

    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
    ῞
    -2.91
    ⟝
    -2.58
    蕷
    -2.52
    ᷆
    -2.48
     conhecida
    -2.44
    ᯅ
    -2.38
    鯪
    -2.36
    푆
    -2.34
    
    -2.34
    齪
    -2.33
    POSITIVE LOGITS
    When
    3.05
    While
    3.02
    During
    2.97
    Although
    2.97
    With
    2.97
    Have
    2.91
    Clearly
    2.83
    Since
    2.80
    What
    2.78
    If
    2.77
    Activations Density 0.004%

    No Known Activations