© 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. 75587
    Prev
    Next
    INDEX
    Explanations

    change date and license

    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
     of
    -1.93
     then
    -1.66
     dieną
    -1.52
     being
    -1.52
     huéspedes
    -1.51
     atento
    -1.51
    menjadi
    -1.47
     it
    -1.45
    mudah
    -1.45
    ǰ
    -1.45
    POSITIVE LOGITS
     will
    1.56
    不愧
    1.52
    $>$
    1.45
     иногда
    1.41
    </em>
    1.41
     to
    1.37
     около
    1.35
     جميع
    1.35
     começar
    1.34
    all
    1.31
    Activations Density 0.030%

    No Known Activations