© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25998
    Prev
    Next
    INDEX
    Explanations

    film makers, cinema, encyclopedia

    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
     or
    -1.91
     one
    -1.60
     an
    -1.52
     your
    -1.43
     can
    -1.41
     typically
    -1.38
     usually
    -1.38
     any
    -1.36
     you
    -1.32
     new
    -1.30
    POSITIVE LOGITS
    
    1.59
    somewhat
    1.45
    nehm
    1.42
    nexo
    1.40
    惋
    1.37
    甗
    1.36
    vements
    1.34
    muir
    1.34
     REASON
    1.34
    かれている
    1.32
    Activations Density 0.018%

    No Known Activations