© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12840
    Prev
    Next
    INDEX
    Explanations

    elle substring

    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
    {
    -3.34
    1
    -3.27
    𔘓
    -2.80
    9
    -2.61
    ネットで
    -2.53
     Beautifully
    -2.53
    鬭
    -2.48
     kleines
    -2.38
     Fairly
    -2.36
     Perfectly
    -2.33
    POSITIVE LOGITS
     então
    2.77
    .”
    2.61
    ⮜
    2.56
    😜
    2.55
    jestel
    2.55
    ments
    2.53
    胧
    2.52
    😛
    2.50
    茈
    2.45
    elle
    2.42
    Activations Density 0.012%

    No Known Activations