© 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. 71446
    Prev
    Next
    INDEX
    Explanations

    string literal expressions

    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
    摀
    -2.67
    id
    -2.50
    am
    -2.47
    y
    -2.28
     chauffage
    -2.28
    j
    -2.23
    东北
    -2.20
     основу
    -2.20
     trochu
    -2.13
    鋇
    -2.13
    POSITIVE LOGITS
    ～　
    2.94
    まさかの
    2.92
    筈
    2.69
    おめでとうございます
    2.66
     
    2.64
    ～～～～
    2.63
    Ideally
    2.53
     That
    2.52
    However
    2.50
    事は
    2.47
    Activations Density 0.003%

    No Known Activations