© 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. 258013
    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
    рах
    0.47
    메
    0.47
    пов
    0.46
    ск
    0.45
    нг
    0.45
    帥
    0.45
    новый
    0.44
    защи
    0.44
    )$.
    0.43
    ствует
    0.43
    POSITIVE LOGITS
     exile
    0.49
     eg
    0.48
    CommandLine
    0.46
     malls
    0.46
    Eg
    0.45
    𝙡
    0.45
    CTOGRAM
    0.45
    AOrdenar
    0.45
     说
    0.44
     गरि
    0.44
    Activations Density 0.004%

    No Known Activations