© 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. 71574
    Prev
    Next
    INDEX
    Explanations

    list and collection declarations

    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
     information
    -1.14
     by
    -1.10
     because
    -1.05
    くださいませ
    -0.99
     how
    -0.98
     data
    -0.98
     and
    -0.96
     within
    -0.95
     problems
    -0.93
    сети
    -0.91
    POSITIVE LOGITS
     gồm
    1.20
     include
    1.20
    cluding
    1.11
     éléments
    1.05
     inkluder
    1.05
     których
    1.05
     aucun
    1.03
     list
    1.03
     segü
    1.02
     RECOMEND
    1.02
    Activations Density 0.014%

    No Known Activations