© 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. 130740
    Prev
    Next
    INDEX
    Explanations

    under the, occupational and, hunting trips

    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
     this
    -1.63
     their
    -1.54
     they
    -1.48
     not
    -1.45
     even
    -1.40
     svých
    -1.19
     one
    -1.19
     nasıl
    -1.16
    şı
    -1.16
     it
    -1.13
    POSITIVE LOGITS
     of
    1.46
    栂
    1.27
     opulent
    1.27
     errichtet
    1.25
    CONTEN
    1.22
     walt
    1.18
     inder
    1.18
     gekenn
    1.15
     Dinas
    1.13
     eingerichtet
    1.13
    Activations Density 0.000%

    No Known Activations