© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99276
    Prev
    Next
    INDEX
    Explanations

    ambient dub music

    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
    -1.47
    diator
    -1.43
     that
    -1.42
     what
    -1.41
    embroidered
    -1.37
    zocht
    -1.32
    antlr
    -1.29
    鳶
    -1.27
     who
    -1.27
    הם
    -1.22
    POSITIVE LOGITS
    ie
    1.35
     surla
    1.34
     télévis
    1.30
    脔
    1.26
    end
    1.25
    chars
    1.21
     departement
    1.20
    Which
    1.20
     mivel
    1.20
    我们
    1.18
    Activations Density 0.016%

    No Known Activations