© 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. 39986
    Prev
    Next
    INDEX
    Explanations

    conjunctions and prepositions

    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
     llorar
    -1.43
     établi
    -1.42
     prétend
    -1.38
     viendra
    -1.35
     japonaise
    -1.34
     despi
    -1.34
     rapidement
    -1.32
     خونه
    -1.32
     rempli
    -1.31
     élar
    -1.31
    POSITIVE LOGITS
     in
    2.23
     but
    2.22
     as
    1.91
     by
    1.77
     because
    1.63
     on
    1.60
     with
    1.49
     without
    1.47
     among
    1.41
     at
    1.40
    Activations Density 0.029%

    No Known Activations