© 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. 123676
    Prev
    Next
    INDEX
    Explanations

    gulls, moons, antidepressant

    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
    {
    -3.44
    ?
    -3.16
    of
    -3.00
    M
    -2.91
    ER
    -2.83
    ve
    -2.75
     If
    -2.72
    ным
    -2.64
    te
    -2.63
    by
    -2.61
    POSITIVE LOGITS
    洐
    2.67
    
    2.59
    靣
    2.52
    ՙ
    2.52
    瀣
    2.47
    亖
    2.47
    徬
    2.45
     撮っ
    2.41
    獁
    2.39
     dále
    2.36
    Activations Density 0.010%

    No Known Activations