© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79954
    Prev
    Next
    INDEX
    Explanations

    of proper nouns

    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
     angep
    -1.17
     equilíbrio
    -1.14
     peculiarly
    -1.13
     предлагает
    -1.12
     hänen
    -1.11
     überprü
    -1.10
     protože
    -1.10
     proclaims
    -1.09
     Succes
    -1.09
     reconhecimento
    -1.07
    POSITIVE LOGITS
     this
    1.49
     after
    1.34
     by
    1.31
     before
    1.31
     if
    1.22
     despite
    1.19
     which
    1.14
     in
    1.14
     just
    1.14
     as
    1.10
    Activations Density 0.070%

    No Known Activations