© 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. 51860
    Prev
    Next
    INDEX
    Explanations

    do make singer NY 8

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

    matching rings

    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
             
    0.47
     {
    0.47
     commenced
    0.46
    >//
    0.46
    >(
    0.45
     パ
    0.45
     二
    0.45
     intersect
    0.44
     commencé
    0.44
    ㄒ
    0.44
    POSITIVE LOGITS
    fetching
    0.52
     Valencia
    0.50
     Nir
    0.49
    vine
    0.47
     iria
    0.46
     अधिक
    0.45
    ्वी
    0.45
    forth
    0.45
    द्धि
    0.44
    pooled
    0.44
    Activations Density 0.000%

    No Known Activations