© 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. 8587
    Prev
    Next
    INDEX
    Explanations

    supplementary

    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
     are
    -2.63
     imprimi
    -2.05
    }$
    -1.91
     kteří
    -1.91
     revamp
    -1.85
     získ
    -1.82
    珍惜
    -1.77
    老虎
    -1.77
    被他
    -1.77
    ultuous
    -1.76
    POSITIVE LOGITS
    you
    2.69
    呖
    2.27
     démocr
    2.23
    谵
    2.20
    ஂ
    2.17
    んび
    2.08
    則是
    2.08
    喈
    2.02
    Fifteen
    2.00
    也沒
    1.96
    Activations Density 0.019%

    No Known Activations