© 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. 84379
    Prev
    Next
    INDEX
    Explanations

    datasets

    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
    }
    -2.77
    禟
    -2.73
    眛
    -2.39
    或
    -2.36
     ddelwed
    -2.36
    鐿
    -2.36
    a
    -2.31
    禤
    -2.20
    ה
    -2.19
    蕺
    -2.17
    POSITIVE LOGITS
     untuk
    3.08
     để
    3.00
     fantástico
    2.53
    ſu
    2.44
     να
    2.44
    to
    2.39
     soo
    2.38
     l
    2.34
    _
    2.28
     alemán
    2.25
    Activations Density 0.004%

    No Known Activations