© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70863
    Prev
    Next
    INDEX
    Explanations

    payouts and winnings

    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
    ’
    -2.42
    .
    -2.38
     This
    -2.13
    }$
    -2.09
    k
    -1.88
     speziellen
    -1.85
     in
    -1.84
    ))=\
    -1.81
    喃
    -1.78
     That
    -1.77
    POSITIVE LOGITS
    ﮦ
    2.44
     всѣ
    2.28
     erwähnten
    2.22
    genodigd
    2.19
    ༷
    2.06
    ーーーー
    2.03
    ーーー
    2.00
     payout
    1.98
    viembre
    1.95
    栳
    1.94
    Activations Density 0.002%

    No Known Activations