© 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. 88965
    Prev
    Next
    INDEX
    Explanations

    foreign words or phrases

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

    flags, teacher, or specific data parameters

    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
     Diameter
    0.48
    Са
    0.46
     न्यूमेरिकल
    0.46
     وذلك
    0.46
    నాలను
    0.45
    嚨
    0.44
     Troubleshooting
    0.44
     Forming
    0.43
    鳎
    0.43
    Where
    0.43
    POSITIVE LOGITS
     bienn
    0.50
     afirm
    0.48
     altar
    0.47
     pagi
    0.47
    rique
    0.46
     liye
    0.46
     ఆధ్యాత్మిక
    0.45
     pix
    0.43
     adal
    0.42
     claust
    0.42
    Activations Density 0.000%

    No Known Activations