© 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. 205928
    Prev
    Next
    INDEX
    Explanations

    about to be

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

    important, crucial, defining characteristic

    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
     Украине
    0.60
     школе
    0.50
    全球
    0.50
     учитель
    0.48
     école
    0.48
     episodio
    0.47
     ljubav
    0.46
     nauczyc
    0.46
    욬
    0.46
     Lehrer
    0.45
    POSITIVE LOGITS
     lign
    0.48
    ille
    0.46
    riz
    0.46
    rice
    0.44
    ry
    0.44
    ett
    0.44
    ithecus
    0.44
    ahari
    0.43
    ile
    0.42
    ino
    0.42
    Activations Density 0.000%

    No Known Activations