© 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. 260747
    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
     carcinogenic
    0.54
    ウ
    0.49
     inactivated
    0.48
    служи
    0.48
    ังสือ
    0.48
    у
    0.47
    󠁳
    0.47
    циона
    0.46
    ціона
    0.46
    ందుకు
    0.46
    POSITIVE LOGITS
     dT
    0.47
     يعمل
    0.47
     Li
    0.47
    结局
    0.43
     Fl
    0.43
     ys
    0.43
     Lit
    0.42
    苍
    0.42
     መጠን
    0.41
    êu
    0.41
    Activations Density 0.002%

    No Known Activations