© 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. 130378
    Prev
    Next
    INDEX
    Explanations

    words starting with cor

    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
    lossians
    -3.33
    
    -2.88
    TintMode
    -2.83
     frecuentemente
    -2.69
    tisone
    -2.69
    恹
    -2.61
    Parcelize
    -2.53
    IndentedString
    -2.52
    cím
    -2.45
     podla
    -2.42
    POSITIVE LOGITS
    ↵
    3.95
    3
    3.42
    ’
    3.16
    0
    3.05
    Y
    3.02
    1
    2.98
    9
    2.94
    an
    2.94
    6
    2.83
    by
    2.80
    Activations Density 0.046%

    No Known Activations