© 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. 22-GEMMASCOPE-RES-131K
    7. 39555
    Prev
    Next
    INDEX
    Explanations

    Premier League

    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_22/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
    "
    -3.47
    ↵↵
    -2.70
     `
    -2.67
    in
    -2.59
     protože
    -2.59
     após
    -2.45
     l
    -2.36
     \&
    -2.34
    },
    -2.31
    所有人都
    -2.30
    POSITIVE LOGITS
    ”،
    3.33
    鶲
    3.00
    錒
    2.63
    酲
    2.52
    隴
    2.47
    儈
    2.45
     bukit
    2.44
    臜
    2.44
    ‪.
    2.42
    茔
    2.41
    Activations Density 0.007%

    No Known Activations