© 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. 133
    Prev
    Next
    INDEX
    Explanations

    existence, development, strengthening, renewal

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

    characteristics and effects

    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
    营收
    0.61
     curviliné
    0.61
     publicités
    0.60
    网红
    0.60
    锺
    0.59
     кеңсесинде
    0.58
    췄
    0.58
    숴
    0.57
    rawdę
    0.56
    满满
    0.56
    POSITIVE LOGITS
     phenomena
    0.59
     manifestations
    0.58
     formations
    0.57
     peculiarities
    0.55
     "
    0.55
     qualitatively
    0.54
     development
    0.50
     the
    0.50
     fragmentary
    0.50
     H
    0.49
    Activations Density 0.049%

    No Known Activations