© 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. 118926
    Prev
    Next
    INDEX
    Explanations

    FDG scans, law, stream, pace

    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
     about
    -2.36
     at
    -2.30
     mostly
    -2.25
     this
    -2.20
     usually
    -2.17
     no
    -2.14
     more
    -2.13
     for
    -2.11
     their
    -2.11
     some
    -2.00
    POSITIVE LOGITS
     avancer
    2.06
     siè
    2.02
     constater
    1.98
     favoriser
    1.92
     faciliter
    1.92
     corriger
    1.90
     zeven
    1.85
     inond
    1.84
     vijf
    1.82
    actéristi
    1.81
    Activations Density 0.170%

    No Known Activations