© 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. 11816
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    鲧
    -1.38
    ⃢
    -1.33
     nader
    -1.32
     مناط
    -1.30
     ſy
    -1.30
    쐈
    -1.26
     baumwolle
    -1.25
     granat
    -1.24
     magaz
    -1.23
     steg
    -1.22
    POSITIVE LOGITS
     that
    1.49
     It
    1.28
     --
    1.26
    Its
    1.24
     how
    1.23
     —
    1.19
     An
    1.18
    —
    1.18
     You
    1.17
     }
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.