© 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. 10-GEMMASCOPE-RES-131K
    4. 124753
    Prev
    Next
    INDEX
    Explanations

    opposition to

    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
    ៚
    -2.17
     intricate
    -1.95
     debatable
    -1.82
    .
    -1.77
    Surprisingly
    -1.75
    of
    -1.74
     frantic
    -1.72
    Since
    -1.67
    ဴ
    -1.66
    
    -1.64
    POSITIVE LOGITS
    鶺
    1.99
     against
    1.91
    忄
    1.84
     carcasa
    1.78
    鸱
    1.77
    鶫
    1.77
    ౬
    1.76
    ೢ
    1.70
    TypedDataSet
    1.70
    这个
    1.70
    Activations Density 0.036%

    No Known Activations