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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45728
    Prev
    Next
    INDEX
    Explanations

    US states and government bodies

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

    The neuron detects mentions of U.S. states (and sometimes the word “United” or “States”)—i.e. geographic/political region names.

    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
    入荷
    -1.05
     İlk
    -1.03
     Якщо
    -1.01
     wollt
    -1.00
     mengakibatkan
    -0.98
     Aktivität
    -0.98
    cuti
    -0.98
    ボトル
    -0.98
    Andere
    -0.97
     Certains
    -0.96
    POSITIVE LOGITS
    L
    1.21
    G
    1.12
     Department
    1.07
     Man
    1.04
    ans
    1.02
    vi
    1.01
    da
    1.00
    ъ
    1.00
     government
    0.98
    FirebaseUser
    0.98
    Activations Density 0.171%

    No Known Activations