© 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. 254304
    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
    ।
    0.51
     выда
    0.48
     .
    0.47
    у
    0.45
     $.
    0.44
    。
    0.44
    ным
    0.44
     శరీ
    0.43
    ским
    0.43
    ный
    0.42
    POSITIVE LOGITS
    \
    0.61
    ٽ
    0.51
    $$_
    0.51
     fortes
    0.50
     grandes
    0.50
     российских
    0.48
    個性
    0.48
    相位
    0.48
    SpringMVCProject
    0.48
     individuality
    0.48
    Activations Density 0.000%

    No Known Activations