© 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. 28618
    Prev
    Next
    INDEX
    Explanations

    html charset declarations

    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
     their
    -2.08
     its
    -1.66
     you
    -1.55
     only
    -1.51
     it
    -1.48
     for
    -1.45
     Schule
    -1.38
     find
    -1.29
     all
    -1.27
     they
    -1.27
    POSITIVE LOGITS
    Aggi
    1.45
     sogenannten
    1.38
     님
    1.37
    roasted
    1.34
     sogenannte
    1.33
     Vergnügen
    1.33
    Enigma
    1.31
    küche
    1.30
     抽象
    1.29
    Begriff
    1.26
    Activations Density 0.001%

    No Known Activations