© 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. 256713
    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
     Россия
    0.52
    acak
    0.51
     दुनिया
    0.50
    ти
    0.49
    ℧
    0.48
    що
    0.48
     Russland
    0.48
     ትንሽ
    0.48
     ವಿಶ್ವ
    0.48
     روسی
    0.47
    POSITIVE LOGITS
     from
    0.52
    )
    0.50
    Park
    0.44
     who
    0.43
    ンド
    0.43
     =
    0.43
    テゴ
    0.42
     Bim
    0.42
     expression
    0.42
     projeto
    0.42
    Activations Density 0.000%

    No Known Activations