© 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. 84841
    Prev
    Next
    INDEX
    Explanations

    craft beer and brews

    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
    鲧
    -2.86
    轳
    -2.63
    ांकि
    -2.58
    鴴
    -2.55
    鹟
    -2.50
    
    -2.39
    说得
    -2.39
     auffi
    -2.36
    艄
    -2.34
    餿
    -2.33
    POSITIVE LOGITS
    a
    3.39
     If
    3.34
    x
    2.95
    ”,
    2.88
    </
    2.81
     jika
    2.78
    If
    2.77
    It
    2.70
    e
    2.59
    担任
    2.55
    Activations Density 0.004%

    No Known Activations