© 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. 41-GEMMASCOPE-2-RES-262K
    7. 25848
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     tooling
    0.45
     viciss
    0.40
     joint
    0.39
    𝒌
    0.38
     masked
    0.37
    kJ
    0.37
     knee
    0.36
     tremendous
    0.36
     chuck
    0.36
     electron
    0.36
    POSITIVE LOGITS
     antiga
    0.55
     antigo
    0.48
     पारंपरिक
    0.48
     antigos
    0.46
     옛
    0.46
    oldt
    0.45
     antiguo
    0.45
    古い
    0.44
     oude
    0.44
     antigua
    0.43
    Activations Density 0.000%

    No Known Activations