© 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. 10-GEMMASCOPE-RES-131K
    4. 9049
    Prev
    Next
    INDEX
    Explanations

    St. followed by 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_10/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
     rembour
    -1.58
     blancs
    -1.50
     refroid
    -1.49
     BEING
    -1.45
     hjemmeside
    -1.41
     GOING
    -1.41
     menik
    -1.41
     juu
    -1.38
     niedersachsen
    -1.36
     flyg
    -1.36
    POSITIVE LOGITS
     by
    1.92
     in
    1.91
     will
    1.86
     out
    1.78
     to
    1.77
     of
    1.75
     those
    1.56
     and
    1.55
     all
    1.48
     Because
    1.46
    Activations Density 0.013%

    No Known Activations