© 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. 69043
    Prev
    Next
    INDEX
    Explanations

    mythological creatures and names

    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
     triom
    -1.55
     fonde
    -1.51
     refroid
    -1.49
     vider
    -1.46
     élas
    -1.45
     deserto
    -1.45
     ekonomi
    -1.44
     contente
    -1.44
     seigneur
    -1.43
     triomphe
    -1.43
    POSITIVE LOGITS
     that
    1.51
     and
    1.36
     reflexiones
    1.35
     of
    1.31
     three
    1.30
     for
    1.29
     five
    1.29
     letzt
    1.28
     people
    1.27
     aufgrund
    1.25
    Activations Density 0.003%

    No Known Activations