© 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. 259992
    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
     excavated
    0.49
     हां
    0.42
     زع
    0.41
    \%
    0.41
    追加
    0.40
     communist
    0.40
     sterilized
    0.40
     cảnh
    0.39
     certamente
    0.39
     socialista
    0.39
    POSITIVE LOGITS
    чёт
    0.54
     담당
    0.53
    хів
    0.52
     刺繍
    0.49
    㸮
    0.48
    кме
    0.48
    Tatar
    0.47
     Tatar
    0.46
    壅
    0.45
    োতে
    0.45
    Activations Density 0.002%

    No Known Activations