© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 252204
    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
    бор
    0.50
    一
    0.46
    atória
    0.46
    uia
    0.46
    بع
    0.45
    <0xA3>
    0.44
    Alice
    0.44
    antec
    0.43
    uv
    0.43
    мора
    0.43
    POSITIVE LOGITS
     mappe
    0.52
     homage
    0.50
     nuovo
    0.47
     protests
    0.47
     ara
    0.46
     structured
    0.46
     (
    0.46
     shown
    0.46
     mapp
    0.45
     most
    0.45
    Activations Density 0.002%

    No Known Activations