© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 234392
    Prev
    Next
    INDEX
    Explanations

    between objects

    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
    Not in Any Lists

    No Comments

    Negative Logits
     неу
    0.48
    nę
    0.48
    lá
    0.47
     сохра
    0.46
     рассматри
    0.46
     расчета
    0.45
    얄
    0.45
     پیسو
    0.44
    лия
    0.44
     ک
    0.44
    POSITIVE LOGITS
     Avon
    0.48
     Motion
    0.47
     Mouth
    0.46
     Makers
    0.46
     akka
    0.45
    শ্ব
    0.45
     adenine
    0.45
     ugg
    0.45
     Suitable
    0.45
     Craft
    0.44
    Activations Density 0.000%

    No Known Activations