© 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. 258834
    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
    敦
    0.51
    .³
    0.48
     машиналарын
    0.48
     HINSTANCE
    0.48
     στι
    0.47
     IERC
    0.47
    HINSTANCE
    0.47
    窕
    0.47
     часу
    0.47
    师
    0.47
    POSITIVE LOGITS
    ek
    0.62
    i
    0.54
    h
    0.51
    ene
    0.50
    ec
    0.50
    o
    0.49
    b
    0.49
    w
    0.49
    te
    0.48
    ad
    0.47
    Activations Density 0.000%

    No Known Activations