© 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. 42074
    Prev
    Next
    INDEX
    Explanations

    feeds and gifts

    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
     also
    -1.37
     either
    -1.35
     to
    -1.27
    MessageWindow
    -1.23
     quietly
    -1.22
     basically
    -1.18
     también
    -1.16
     equally
    -1.15
     especially
    -1.13
     Möglich
    -1.11
    POSITIVE LOGITS
     nossa
    1.33
     県
    1.27
     our
    1.27
    лить
    1.23
     }_{
    1.23
     kaplama
    1.23
     nossos
    1.22
     digno
    1.22
     السياس
    1.20
     we
    1.17
    Activations Density 0.038%

    No Known Activations