© 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. 22-GEMMASCOPE-RES-131K
    7. 40183
    Prev
    Next
    INDEX
    Explanations

    need to do something

    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_22/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
     poë
    -0.95
     créer
    -0.95
    quête
    -0.94
    locene
    -0.94
     Veränder
    -0.91
    avoid
    -0.90
    hile
    -0.89
     appétit
    -0.89
     usando
    -0.88
    ined
    -0.86
    POSITIVE LOGITS
     instantly
    1.41
     quickly
    1.41
     immediately
    1.32
     swiftly
    1.23
     usually
    1.22
     always
    1.16
     resorted
    1.10
     one
    1.08
     vždy
    1.07
     quick
    1.06
    Activations Density 0.043%

    No Known Activations