© 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. 127346
    Prev
    Next
    INDEX
    Explanations

    golang.org, k8s.io, google.golang

    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
     to
    -2.67
    3
    -1.91
     this
    -1.84
    5
    -1.81
     erwähnt
    -1.79
    1
    -1.78
    0
    -1.77
    4
    -1.72
    7
    -1.67
     another
    -1.63
    POSITIVE LOGITS
    \
    1.78
     puits
    1.66
    šanās
    1.65
    峮
    1.61
     ferie
    1.61
    МЫ
    1.57
    vių
    1.56
    <bos>
    1.55
    省市镇
    1.55
    雠
    1.54
    Activations Density 0.039%

    No Known Activations