© 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. 233016
    Prev
    Next
    INDEX
    Explanations

    all, strong, engines, sites, hotels, manufacturers

    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
     국가
    0.43
    citing
    0.43
    争议
    0.43
     संर
    0.42
    ›
    0.42
     科
    0.42
     약간
    0.42
    莠
    0.42
    캄
    0.41
    좔
    0.41
    POSITIVE LOGITS
     Lucifer
    0.46
     velocidade
    0.45
     lossless
    0.45
     hiper
    0.44
     douleur
    0.43
     Enfer
    0.43
     iPhone
    0.42
     restant
    0.42
     pesar
    0.42
     autopsy
    0.41
    Activations Density 0.001%

    No Known Activations