© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 216215
    Prev
    Next
    INDEX
    Explanations

    Prime Minister, provider, specific software

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

    LLMs and specific terms

    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
    Negative Logits
     American
    0.47
     Chemical
    0.47
     couture
    0.46
     sculpted
    0.46
     ultram
    0.45
     vari
    0.45
     neodymium
    0.44
     sculpting
    0.44
     \*
    0.43
     mousse
    0.43
    POSITIVE LOGITS
    initState
    0.48
    periods
    0.46
    それは
    0.46
    蹉
    0.44
    👮
    0.44
     अवज्ञा
    0.43
    ありがとう
    0.43
    Y
    0.43
    waitTime
    0.43
    gridView
    0.42
    Activations Density 0.000%

    No Known Activations