© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59520
    Prev
    Next
    INDEX
    Explanations

    government officers

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

    This neuron identifies dense, formal legal or bureaucratic passages—sections of administrative text defining provisions and categories.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gob
    -0.81
     鳳
    -0.79
     mobilier
    -0.78
     benzin
    -0.76
     Sicherheits
    -0.75
     Стали
    -0.75
    Jenkins
    -0.74
    ukau
    -0.74
    Τα
    -0.74
    ABIL
    -0.74
    POSITIVE LOGITS
     officer
    0.90
    𝒆
    0.78
     Officers
    0.77
     OFFICER
    0.75
    ,]
    0.75
     Officer
    0.74
    ckey
    0.73
    officer
    0.73
     officers
    0.72
    อะไร
    0.72
    Activations Density 0.007%

    No Known Activations