© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19471
    Prev
    Next
    INDEX
    Explanations

    dimensions separated by x

    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
    </h2>
    -1.89
    However
    -1.83
     欣赏
    -1.79
    Unfortunately
    -1.76
     But
    -1.74
    </sup>
    -1.66
    </h4>
    -1.65
    mathrm
    -1.55
    isation
    -1.54
     nhưng
    -1.54
    POSITIVE LOGITS
     we
    2.17
    '
    2.13
     such
    2.11
    </i>
    1.67
     they
    1.63
     unless
    1.58
     you
    1.55
     of
    1.53
     gdyby
    1.51
     \'
    1.50
    Activations Density 0.013%

    No Known Activations