© 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. 40577
    Prev
    Next
    INDEX
    Explanations

    account login and password

    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
    {
    -2.19
    }
    -1.93
    [
    -1.84
    鹵
    -1.80
    ↠
    -1.80
    掬
    -1.79
     этом
    -1.78
    )
    -1.74
    ѣмъ
    -1.70
    ’
    -1.67
    POSITIVE LOGITS
    觊
    1.75
    理会
    1.67
     soprattutto
    1.59
     Ведь
    1.59
     треть
    1.55
     使っ
    1.55
     Fundament
    1.52
     Потому
    1.50
    經歷
    1.49
     prud
    1.48
    Activations Density 0.022%

    No Known Activations