© 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. 195087
    Prev
    Next
    INDEX
    Explanations

    instantly, family, previous, dump

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

    inverse transformation

    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
    支
    0.52
    ம்
    0.49
    ์
    0.47
    セ
    0.47
    ти
    0.47
    ें
    0.46
    ми
    0.46
    ре
    0.46
    セット
    0.46
    лли
    0.45
    POSITIVE LOGITS
     Hamming
    0.52
     excreted
    0.51
     CuO
    0.50
     Angaben
    0.49
    läger
    0.49
     effectually
    0.49
     Bourd
    0.49
     Hilbert
    0.49
    ktions
    0.48
     Shun
    0.48
    Activations Density 0.000%

    No Known Activations