© 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. 256232
    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
    ಡುಗೆ
    0.52
    ർ
    0.52
    াহার
    0.51
    ત્રો
    0.51
    亼
    0.50
    崱
    0.50
    মানুষ
    0.50
    푞
    0.49
    ബർ
    0.49
    മ്പർ
    0.48
    POSITIVE LOGITS
     بدل
    0.47
    *
    0.47
    _
    0.47
     canal
    0.45
     obliquely
    0.45
    i
    0.45
    c
    0.44
    ar
    0.44
    a
    0.44
     sidewalk
    0.44
    Activations Density 0.000%

    No Known Activations