© 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. 1374
    Prev
    Next
    INDEX
    Explanations

    at any time

    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
    łby
    -1.57
     vong
    -1.43
     駅前
    -1.43
     какая
    -1.34
     lenta
    -1.33
     ilang
    -1.33
     diagnostica
    -1.30
     gustos
    -1.30
     montrent
    -1.28
    踽
    -1.27
    POSITIVE LOGITS
     during
    1.88
     if
    1.70
     إذا
    1.62
     to
    1.56
     the
    1.44
     at
    1.41
     JMenuItem
    1.38
     Regardless
    1.36
     CGRectMake
    1.35
    However
    1.34
    Activations Density 0.034%

    No Known Activations