© 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. 91759
    Prev
    Next
    INDEX
    Explanations

    submitted via

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

    LZW algorithm encoding/compression

    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
    ى
    0.61
    وری
    0.51
    ките
    0.47
    wara
    0.47
    ке
    0.47
    wq
    0.46
    p
    0.46
    κε
    0.45
    ofs
    0.45
     फिस
    0.45
    POSITIVE LOGITS
     daff
    0.59
     gold
    0.52
     do
    0.51
     window
    0.49
     solved
    0.48
     MILL
    0.48
    India
    0.47
     mines
    0.46
     naut
    0.46
     cruising
    0.46
    Activations Density 0.000%

    No Known Activations