© 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. 254141
    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
    ⅰ
    0.49
     calcareous
    0.47
     recomm
    0.47
     resumed
    0.47
     끼
    0.47
     restarting
    0.45
     재생
    0.45
    typically
    0.44
     consequ
    0.43
    ಟ್ಟ
    0.42
    POSITIVE LOGITS
    ilmente
    0.46
    ColorF
    0.45
    butan
    0.45
    ̢
    0.44
    াধিকার
    0.44
    েক
    0.43
    簱
    0.43
    间隔
    0.43
    essa
    0.42
    patched
    0.42
    Activations Density 0.000%

    No Known Activations