© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129137
    Prev
    Next
    INDEX
    Explanations

    hike, Miguel, Ramon

    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
    ”
    -3.23
    de
    -3.03
    s
    -2.92
    co
    -2.80
    ling
    -2.70
    <em>
    -2.66
    鱟
    -2.56
    the
    -2.55
    ag
    -2.55
    </h3>
    -2.55
    POSITIVE LOGITS
    崀
    2.67
     katkıda
    2.53
    籥
    2.39
    genodigd
    2.38
     reú
    2.34
     protegida
    2.28
    絝
    2.28
     soñ
    2.28
     koruyucu
    2.27
    फ्त
    2.25
    Activations Density 0.001%

    No Known Activations