© 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. 13862
    Prev
    Next
    INDEX
    Explanations

    family members and children

    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
     something
    -1.23
     continued
    -1.23
     might
    -1.22
     will
    -1.21
     should
    -1.16
     being
    -1.16
     some
    -1.16
     different
    -1.15
     their
    -1.14
     or
    -1.12
    POSITIVE LOGITS
     who
    1.45
     gants
    1.33
     Tô
    1.32
     plafon
    1.29
     pelu
    1.23
     attente
    1.22
     ibadah
    1.21
    👨
    1.21
     bandes
    1.20
     bross
    1.20
    Activations Density 0.040%

    No Known Activations