© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90700
    Prev
    Next
    INDEX
    Explanations

    Raven

    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
    \
    -2.94
    翃
    -2.84
    轳
    -2.75
    P
    -2.64
    榈
    -2.48
    踭
    -2.47
     elevate
    -2.44
    摃
    -2.41
    骉
    -2.39
    ations
    -2.36
    POSITIVE LOGITS
    鵟
    2.95
    sukienka
    2.70
    璈
    2.56
     thut
    2.48
    .''
    2.48
    獁
    2.45
     łóż
    2.42
     kuchen
    2.25
     afbeelding
    2.22
    ࿙
    2.22
    Activations Density 0.002%

    No Known Activations