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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 564
    Prev
    Next
    INDEX
    Explanations

    baking and kubernetes

    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
    犇
    -2.88
    屃
    -2.53
    뭄
    -2.38
    と
    -2.33
    ’
    -2.28
     wydaje
    -2.23
    玬
    -2.17
     díky
    -2.16
    ?’
    -2.14
    が存在
    -2.09
    POSITIVE LOGITS
    o
    3.75
    -
    2.59
    a
    2.52
    t
    2.47
    --
    2.47
     quelques
    2.34
    e
    2.27
     thee
    2.27
    {
    2.27
    剮
    2.25
    Activations Density 0.001%

    No Known Activations