© 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. 235446
    Prev
    Next
    INDEX
    Explanations

    assassins and nations

    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
     दिर
    0.54
    unier
    0.48
    இந்த
    0.47
    blick
    0.45
    ckiej
    0.45
    reliable
    0.45
     Zeitschrift
    0.44
    ☹
    0.44
     resuspended
    0.44
    neutrophiles
    0.44
    POSITIVE LOGITS
    Assassin
    0.49
     نسخ
    0.45
     jacks
    0.44
    人为
    0.44
     operar
    0.43
     Assassin
    0.43
     وطن
    0.43
     رجل
    0.43
     nation
    0.43
     geopol
    0.42
    Activations Density 0.000%

    No Known Activations