© 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. 192632
    Prev
    Next
    INDEX
    Explanations

    eclectic mix, German proposal

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

    missing nickel

    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
     gesprek
    0.50
     socalled
    0.48
    ック
    0.47
     wir
    0.47
     weniger
    0.47
     跟
    0.45
     niet
    0.45
    哽
    0.45
     obč
    0.45
     parti
    0.44
    POSITIVE LOGITS
    urine
    0.57
    solutions
    0.54
    Handbook
    0.54
    embryon
    0.52
    ALES
    0.52
    MESSAGE
    0.51
    protocols
    0.51
    Solutions
    0.50
    lices
    0.50
    OPS
    0.50
    Activations Density 0.000%

    No Known Activations