© 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. 48396
    Prev
    Next
    INDEX
    Explanations

    question words and beginnings of phrases

    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
     and
    -1.83
     after
    -1.53
     this
    -1.51
    pēc
    -1.50
     before
    -1.45
    struzioni
    -1.45
    %");
    -1.44
     giocatori
    -1.37
    tichetta
    -1.36
     fisuras
    -1.36
    POSITIVE LOGITS
     verhind
    1.51
    甗
    1.38
     =
    1.34
     the
    1.30
     are
    1.28
    了
    1.27
    1
    1.27
    你现在
    1.25
     lleve
    1.24
    却被
    1.23
    Activations Density 0.110%

    No Known Activations