© 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. 65504
    Prev
    Next
    INDEX
    Explanations

    number of

    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
     scrutin
    -1.89
    뚠
    -1.76
    苼
    -1.73
     somewhat
    -1.71
    臜
    -1.70
     الأخرى
    -1.67
    ER
    -1.63
    䛗
    -1.62
    uſe
    -1.58
    ᠂
    -1.56
    POSITIVE LOGITS
     of
    2.53
     to
    2.02
     it
    1.89
     which
    1.75
     from
    1.63
     any
    1.57
     After
    1.51
     in
    1.45
     your
    1.45
     papild
    1.41
    Activations Density 0.036%

    No Known Activations