© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 193357
    Prev
    Next
    INDEX
    Explanations

    bureau of

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

    Bureau of government agencies

    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
    Not in Any Lists

    No Comments

    Negative Logits
     período
    0.46
     periodo
    0.46
     (-\
    0.45
    quinazoline
    0.44
    ראל
    0.43
     singolo
    0.42
    it
    0.42
     follower
    0.42
     পরিপূর্ণ
    0.42
     pranzo
    0.42
    POSITIVE LOGITS
     bureaux
    0.59
     бюро
    0.58
    Bureau
    0.55
     Bureau
    0.52
    별
    0.47
    ⤥
    0.45
     bureau
    0.44
    JER
    0.44
     BUREAU
    0.44
     પડ
    0.43
    Activations Density 0.016%

    No Known Activations