© 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. 11198
    Prev
    Next
    INDEX
    Explanations

    bike and related activities or places

    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
    ’
    -3.98
    ↵
    -3.72
     –
    -3.23
    l
    -3.00
    7
    -2.83
    <em>
    -2.83
    _{
    -2.81
    ”
    -2.80
    缡
    -2.73
    …)
    -2.63
    POSITIVE LOGITS
    ſam
    3.05
    鉭
    3.02
    ዡ
    2.97
     绒
    2.81
    ﮟ
    2.64
     gefährlich
    2.63
    詒
    2.63
    したので
    2.59
    urnum
    2.58
     война
    2.56
    Activations Density 0.005%

    No Known Activations