© 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. 87042
    Prev
    Next
    INDEX
    Explanations

    tied to record or level

    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
    </h3>
    -1.66
    </h2>
    -1.66
     sogenannte
    -1.53
    n
    -1.52
    -
    -1.52
    ated
    -1.52
    ating
    -1.46
    зывы
    -1.46
    lognese
    -1.43
     rumbling
    -1.43
    POSITIVE LOGITS
     on
    1.85
     his
    1.73
    of
    1.65
    priest
    1.63
     our
    1.63
     have
    1.54
     tênis
    1.52
     รี
    1.48
     for
    1.45
     lainnya
    1.41
    Activations Density 0.006%

    No Known Activations