© 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. 254165
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     titulares
    0.55
     Trotz
    0.47
     haunting
    0.46
     sicherlich
    0.46
    գ
    0.46
     haunt
    0.46
     kurie
    0.45
    crunch
    0.45
    ()}>
    0.43
    들을
    0.43
    POSITIVE LOGITS
     intercellular
    0.44
     autobus
    0.44
     ถนน
    0.44
    Lyn
    0.44
     ř
    0.43
     فتح
    0.43
    褙
    0.43
    ায়ের
    0.41
    ২৪
    0.41
     автобу
    0.41
    Activations Density 0.000%

    No Known Activations