© 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. 22-GEMMASCOPE-RES-131K
    7. 39230
    Prev
    Next
    INDEX
    Explanations

    song descriptions

    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
    číta
    -1.41
     będzie
    -1.41
    ֶּ
    -1.38
     piensan
    -1.29
     wensen
    -1.27
    すっ
    -1.24
     délais
    -1.23
     sélectionner
    -1.23
     السياس
    -1.23
    dây
    -1.23
    POSITIVE LOGITS
     featuring
    1.46
     if
    1.29
     InputDecoration
    1.26
     again
    1.23
     another
    1.23
     marinho
    1.20
     where
    1.19
     just
    1.18
     I
    1.10
    Pranala
    1.09
    Activations Density 0.014%

    No Known Activations