© 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. 23999
    Prev
    Next
    INDEX
    Explanations

    territory or line

    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
     ženy
    -1.63
    orius
    -1.44
     dáms
    -1.40
    actually
    -1.39
    still
    -1.38
    truly
    -1.38
     suspensão
    -1.36
     malheure
    -1.34
     nettoy
    -1.34
     вони
    -1.34
    POSITIVE LOGITS
     \
    1.69
     only
    1.67
    '
    1.52
     their
    1.43
     even
    1.36
     line
    1.34
     I
    1.32
     '';
    1.30
    ........
    1.27
     control
    1.27
    Activations Density 0.007%

    No Known Activations