© 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. 22-GEMMASCOPE-RES-131K
    7. 93137
    Prev
    Next
    INDEX
    Explanations

    Las Vegas, Nevada

    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_22/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
    絰
    -1.73
    '...
    -1.62
    ⼗
    -1.61
     AGUA
    -1.59
    ྰ
    -1.56
    涐
    -1.48
     різних
    -1.46
     ALLA
    -1.43
     Coleridge
    -1.42
     薬局
    -1.41
    POSITIVE LOGITS
     —
    1.59
    ,
    1.47
     Las
    1.41
     –
    1.41
    秾
    1.39
     Nevada
    1.38
     Your
    1.34
    пыта
    1.32
    阗
    1.32
     was
    1.30
    Activations Density 0.021%

    No Known Activations