© 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. 1889
    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
    蝙
    0.51
    蕉
    0.45
    لام
    0.44
    aliyet
    0.44
    奸
    0.43
    ح
    0.43
     feeder
    0.42
    胃
    0.42
    芾
    0.42
    ra
    0.41
    POSITIVE LOGITS
     accommodate
    0.59
     cuadrados
    0.52
     accumulates
    0.51
     монасты
    0.51
     accommodates
    0.51
     optimise
    0.50
    填充
    0.49
     dissolves
    0.49
     monasteries
    0.49
    :
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.