© 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. 78089
    Prev
    Next
    INDEX
    Explanations

    objects, marketing, employment, mammals

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

    chasing string, lives near, conservation status

    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
     mémoire
    0.48
    americano
    0.47
    ifiée
    0.47
    āya
    0.46
    assertions
    0.45
    ందరు
    0.44
    📮
    0.44
    ětí
    0.43
    땄
    0.43
    ónico
    0.42
    POSITIVE LOGITS
     Education
    0.51
     教育
    0.47
     Wages
    0.47
     Philosophy
    0.46
     Fach
    0.45
     Reich
    0.44
     Prostate
    0.44
     Skinner
    0.44
     Wikis
    0.44
     Shack
    0.44
    Activations Density 0.001%

    No Known Activations