© 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. 13350
    Prev
    Next
    INDEX
    Explanations

    behavior of quantities or states

    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
     publier
    -1.45
     takiego
    -1.39
     déposer
    -1.38
     décider
    -1.38
     olacaktır
    -1.37
    摃
    -1.34
     gestire
    -1.33
    噘
    -1.33
     sicht
    -1.32
     スクエア
    -1.30
    POSITIVE LOGITS
     at
    2.53
     only
    2.31
     even
    1.88
     there
    1.68
     all
    1.55
     in
    1.49
     when
    1.44
     remun
    1.44
     There
    1.39
     Only
    1.38
    Activations Density 0.189%

    No Known Activations