© 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. 108629
    Prev
    Next
    INDEX
    Explanations

    car bombs, attacks, GM, updates, trails

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

    comparison and purpose

    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
     priced
    0.51
     donn
    0.44
     titans
    0.43
    <0x92>
    0.43
     recherche
    0.43
     ministers
    0.43
     costing
    0.43
     fraught
    0.43
     desperately
    0.42
     contracted
    0.42
    POSITIVE LOGITS
     ກ
    0.55
     อนุ
    0.54
     Ανα
    0.52
     เพ
    0.50
     ສ
    0.50
     Trails
    0.50
    𝑇
    0.49
    ld
    0.49
     ลักษณะ
    0.48
    𝑡
    0.48
    Activations Density 0.001%

    No Known Activations