© 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. 84472
    Prev
    Next
    INDEX
    Explanations

    contextual prepositions or indicators

    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
    generally
    -1.41
     autonomie
    -1.40
     offrent
    -1.39
    ఽ
    -1.37
    粜
    -1.35
     alcuni
    -1.33
    ophiles
    -1.32
     alcune
    -1.32
     manifeste
    -1.31
     devraient
    -1.30
    POSITIVE LOGITS
     or
    1.94
     like
    1.59
     and
    1.57
     such
    1.48
     at
    1.42
     remain
    1.38
     so
    1.35
     because
    1.31
     still
    1.24
     on
    1.23
    Activations Density 0.628%

    No Known Activations