© 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. 1696
    Prev
    Next
    INDEX
    Explanations

    auto-generated, auto-completion, auto-configure

    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
     The
    -2.20
     But
    -2.09
     cuja
    -2.03
     to
    -1.99
     Of
    -1.99
    
    -1.89
    "",
    
    -1.84
    pecabe
    -1.80
    mpagne
    -1.77
     conhecida
    -1.73
    POSITIVE LOGITS
    After
    2.48
    Through
    2.25
    Since
    2.25
    an
    2.19
    Ведущий
    2.14
    e
    2.09
    Following
    2.08
    For
    2.08
    Having
    2.05
    Because
    2.03
    Activations Density 0.003%

    No Known Activations