© 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. 129
    Prev
    Next
    INDEX
    Explanations

    said that

    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
     what
    -1.78
    鵟
    -1.77
    When
    -1.71
    Además
    -1.68
    Jika
    -1.66
    Они
    -1.66
    Также
    -1.65
     When
    -1.59
     дуже
    -1.58
     also
    -1.57
    POSITIVE LOGITS
    ↵↵
    1.93
     “
    1.57
     is
    1.48
     announces
    1.37
     be
    1.33
     sum
    1.33
    </u>
    1.32
     on
    1.31
    hose
    1.26
    = 
    1.26
    Activations Density 0.030%

    No Known Activations