© 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. 86149
    Prev
    Next
    INDEX
    Explanations

    document references

    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
     of
    -1.87
     in
    -1.57
    際には
    -1.45
     they
    -1.39
    ၞ
    -1.34
    lytes
    -1.32
     khususnya
    -1.30
     for
    -1.30
    撈
    -1.28
     使っ
    -1.27
    POSITIVE LOGITS
     who
    1.45
     empezó
    1.41
    }=\
    1.37
    τής
    1.35
     comien
    1.31
     —
    1.31
    archiwizowane
    1.30
    ?“
    1.30
     tunik
    1.28
    政府
    1.23
    Activations Density 0.070%

    No Known Activations