© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 251063
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gravida
    0.56
    ktCap
    0.51
    ড়ান্ত
    0.51
    лимпи
    0.49
    >*</
    0.48
    StarObject
    0.46
    ියා
    0.46
    пили
    0.46
    Brainz
    0.46
    LockButton
    0.45
    POSITIVE LOGITS
    when
    0.55
    im
    0.51
    oz
    0.51
    as
    0.50
    ose
    0.49
    ved
    0.49
     y
    0.49
    sor
    0.49
    os
    0.49
     when
    0.48
    Activations Density 0.002%

    No Known Activations