© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22117
    Prev
    Next
    INDEX
    Explanations

    CSA and Marianne name contexts

    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
    櫚
    -2.84
    0
    -2.83
    with
    -2.69
    榈
    -2.67
    のお知らせ
    -2.52
    1
    -2.48
     obispo
    -2.45
    相當
    -2.44
     Veränder
    -2.44
    鞏
    -2.34
    POSITIVE LOGITS
    塤
    2.95
    翆
    2.80
    哢
    2.75
    ⬮
    2.48
    銫
    2.41
    al
    2.38
    
    2.36
    </h1>
    2.34
    ××
    2.31
     \%$.
    2.30
    Activations Density 0.009%

    No Known Activations