© 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. 34-GEMMASCOPE-RES-131K
    4. 6986
    Prev
    Next
    INDEX
    Explanations

    attribute closing brackets

    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_34/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
     it
    -1.25
     so
    -1.22
     or
    -1.14
     all
    -1.04
     for
    -1.00
    <eos>
    -1.00
     [
    -0.99
    :
    -0.97
     from
    -0.96
     their
    -0.94
    POSITIVE LOGITS
    ")]
    1.19
     extremamente
    1.14
    욤
    1.10
    了啊
    1.07
    Produits
    1.05
     بيها
    1.04
    Etape
    1.01
     炒め
    1.01
     pousser
    1.01
    ופי
    1.00
    Activations Density 0.001%

    No Known Activations