© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123863
    Prev
    Next
    INDEX
    Explanations

    requirements and instructions

    np_acts-logits-general · gemini-2.5-flash-lite

    ligaments, Aristotle, controls, significantly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dimers
    0.47
     secundarios
    0.45
     aumento
    0.45
     Khanna
    0.44
    </h2>
    0.44
     SUCH
    0.44
     dimerization
    0.43
    </h1>
    0.43
     parceria
    0.43
     manz
    0.43
    POSITIVE LOGITS
    苏州
    0.54
    gür
    0.50
    subscriber
    0.47
    ፕሮ
    0.47
    gins
    0.46
    Prest
    0.45
    tStart
    0.45
    trong
    0.45
    edia
    0.44
    tent
    0.44
    Activations Density 0.001%

    No Known Activations