© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10503
    Prev
    Next
    INDEX
    Explanations

    cities followed by a comma

    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
    already
    -1.77
    就已经
    -1.59
    a
    -1.59
    Already
    -1.54
    including
    -1.47
    何も
    -1.45
    Actually
    -1.36
    3
    -1.36
    specifically
    -1.34
    i
    -1.34
    POSITIVE LOGITS
     of
    3.27
     from
    1.56
     理由
    1.30
     That
    1.29
    😍😍
    1.28
     they
    1.26
     架
    1.26
     musíte
    1.25
    woorden
    1.24
    дву
    1.23
    Activations Density 0.176%

    No Known Activations