© 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. 72880
    Prev
    Next
    INDEX
    Explanations

    understand or knowledge

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

    foreign languages and media

    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
     centrales
    0.56
    ਰਾ
    0.45
     humides
    0.44
    अ
    0.43
    न्न
    0.43
     limites
    0.43
     enzimas
    0.43
    অ
    0.43
    अमेरिका
    0.42
     kapcs
    0.42
    POSITIVE LOGITS
    未经
    0.50
     Phi
    0.47
     Melo
    0.46
    skie
    0.45
     Photos
    0.45
    ვით
    0.44
     Beschreibung
    0.44
     Hampton
    0.44
     அற்புதமான
    0.44
     Georgetown
    0.43
    Activations Density 0.001%

    No Known Activations