© 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. 13238
    Prev
    Next
    INDEX
    Explanations

    HTML span tags

    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
    鹚
    -2.58
    going
    -2.52
    🧌
    -2.42
     新款
    -2.36
    咈
    -2.28
    鼯
    -2.22
    梛
    -2.22
    
    -2.17
    盌
    -2.13
    つた
    -2.09
    POSITIVE LOGITS
    e
    3.22
    ?
    2.81
    饪
    2.69
    p
    2.48
    赑
    2.41
    f
    2.36
    ed
    2.34
    a
    2.33
    in
    2.27
     of
    2.27
    Activations Density 0.008%

    No Known Activations