© 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. 13720
    Prev
    Next
    INDEX
    Explanations

    episodes of tv shows

    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
     then
    -1.88
     by
    -1.86
    0
    -1.82
     what
    -1.76
     know
    -1.59
     who
    -1.52
     knew
    -1.48
     \
    -1.48
     understand
    -1.48
     get
    -1.45
    POSITIVE LOGITS
     épisodes
    1.77
    Kf
    1.70
    "}}>
    1.65
     Franse
    1.64
     normale
    1.63
     nacht
    1.62
    𝓣
    1.60
    𓇼
    1.57
     liquide
    1.56
     of
    1.55
    Activations Density 0.053%

    No Known Activations