© 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. 29090
    Prev
    Next
    INDEX
    Explanations

    honorable titles followed by names

    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
    viembre
    -1.70
    </h4>
    -1.66
     gebeurt
    -1.57
     proporciona
    -1.55
    íte
    -1.55
    泐
    -1.52
     anuncia
    -1.52
     recibe
    -1.50
    が少ない
    -1.46
     möj
    -1.45
    POSITIVE LOGITS
     will
    1.86
     and
    1.52
     only
    1.33
    is
    1.33
     three
    1.31
    the
    1.29
     H
    1.28
    there
    1.28
    Ｍ
    1.27
    There
    1.27
    Activations Density 0.006%

    No Known Activations