© 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. 11143
    Prev
    Next
    INDEX
    Explanations

    bound to lose

    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
     délais
    -2.36
     of
    -2.08
     coûts
    -2.06
     inconvénients
    -1.99
     ito
    -1.91
     acqua
    -1.89
     précieux
    -1.88
     čier
    -1.84
     facili
    -1.84
    BUT
    -1.84
    POSITIVE LOGITS
     as
    2.48
     or
    2.47
     so
    2.44
     mostly
    2.38
     mainly
    2.25
     primarily
    2.16
     and
    2.16
     probably
    2.11
     entirely
    2.09
     difficult
    2.08
    Activations Density 0.160%

    No Known Activations