© 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. 38651
    Prev
    Next
    INDEX
    Explanations

    biblical figures and terms

    np_acts-logits-general · gemini-2.5-flash-lite

    shall not lie

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     loss
    0.38
     escape
    0.37
    慟
    0.34
     restorations
    0.34
     roofs
    0.33
    erns
    0.33
     suff
    0.33
     falla
    0.32
    ↵↵↵↵↵↵
    0.31
     silence
    0.31
    POSITIVE LOGITS
    NeedConnect
    0.49
    BlockFit
    0.42
    🍔
    0.41
    ель
    0.39
    🌮
    0.39
    你可以
    0.38
    🍪
    0.38
     Colgate
    0.38
     मैने
    0.37
    CCOC
    0.37
    Activations Density 0.031%

    No Known Activations