© 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. 40354
    Prev
    Next
    INDEX
    Explanations

    specific locations after "in"

    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
     både
    -1.48
     sorento
    -1.38
     problemet
    -1.32
     sportage
    -1.31
     Situs
    -1.30
     boute
    -1.30
    鸨
    -1.30
     Responsable
    -1.29
     hybride
    -1.28
     pernic
    -1.27
    POSITIVE LOGITS
     within
    1.40
     just
    1.38
     after
    1.34
     no
    1.33
     at
    1.31
     If
    1.30
     before
    1.28
     These
    1.28
     only
    1.23
     near
    1.22
    Activations Density 0.056%

    No Known Activations