© 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. 114133
    Prev
    Next
    INDEX
    Explanations

    biggest challenges, maximize

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

    contrastive conjunctions

    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
     Firefox
    0.49
    🥂
    0.48
     journalist
    0.48
     Desktop
    0.47
     גר
    0.47
     supercar
    0.46
    🦠
    0.46
     desktop
    0.46
     брау
    0.46
     firefox
    0.46
    POSITIVE LOGITS
     própria
    0.46
    另外
    0.44
     जिसमें
    0.43
    Bearing
    0.43
    儿
    0.41
    хів
    0.41
     calyce
    0.40
    G
    0.40
    refs
    0.40
     බව
    0.39
    Activations Density 0.000%

    No Known Activations