© 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. 90872
    Prev
    Next
    INDEX
    Explanations

    specify, declare, define, showcase

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

    technical terms and policies

    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
     beware
    0.47
     tribun
    0.45
     Tribun
    0.44
    ה
    0.43
    nya
    0.43
     값
    0.42
    觧
    0.42
     ܠ
    0.42
     Пари
    0.41
     وقف
    0.41
    POSITIVE LOGITS
     prototypical
    0.57
     will
    0.48
     genannten
    0.46
    раль
    0.46
     mittel
    0.46
     centerline
    0.46
     archaeological
    0.45
     incoherent
    0.45
     definitive
    0.44
    ান্ডের
    0.44
    Activations Density 0.000%

    No Known Activations