© 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. 119814
    Prev
    Next
    INDEX
    Explanations

    sports actions and outcomes

    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
    xically
    -1.70
    titial
    -1.68
    zzlement
    -1.63
    itados
    -1.58
    了一遍
    -1.48
     їх
    -1.47
    slot
    -1.46
     chré
    -1.45
     PUSTAKA
    -1.45
    tifs
    -1.43
    POSITIVE LOGITS
     of
    2.39
     then
    2.20
     by
    2.02
     the
    1.99
    ためには
    1.95
     between
    1.77
     to
    1.77
     about
    1.74
     at
    1.73
    当時の
    1.73
    Activations Density 0.020%

    No Known Activations