© 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. 66585
    Prev
    Next
    INDEX
    Explanations

    debut works

    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
    ⟝
    -2.14
    
    -1.86
     MÁS
    -1.74
    釭
    -1.66
    쨩
    -1.63
    
    -1.62
    »,
    -1.57
    árbol
    -1.55
    閦
    -1.55
     DÍA
    -1.53
    POSITIVE LOGITS
    ing
    2.56
     that
    1.98
    ة
    1.95
    o
    1.62
     如何
    1.48
     of
    1.48
    (
    1.46
     escova
    1.45
     achet
    1.42
    getCause
    1.41
    Activations Density 0.009%

    No Known Activations