© 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. 105769
    Prev
    Next
    INDEX
    Explanations

    ends of code statements

    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
    :
    -1.97
    us
    -1.72
     —
    -1.70
     ليس
    -1.61
    where
    -1.57
    k
    -1.55
     of
    -1.54
    without
    -1.51
    ſſer
    -1.50
    ter
    -1.48
    POSITIVE LOGITS
     your
    1.98
    ociação
    1.87
    ▤
    1.82
     ontwikkeling
    1.79
     Eröffnung
    1.78
    ってみて
    1.77
    kenstock
    1.77
     gezondheid
    1.75
     diensten
    1.74
    iyi
    1.73
    Activations Density 0.021%

    No Known Activations