© 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. 11844
    Prev
    Next
    INDEX
    Explanations

    Community Initiatives and Networks

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

    The neuron activates on words related to sanitation and public defecation (e.g., open defecation, public toilets, hygiene).

    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
    (';
    -0.75
     cooling
    -0.73
    Charles
    -0.71
    泄
    -0.71
     برج
    -0.71
     Kno
    -0.69
    ＋
    -0.68
    PopupWindow
    -0.68
    opened
    -0.67
    Fri
    -0.66
    POSITIVE LOGITS
     Rankings
    0.93
     Eritrea
    0.87
    جوی
    0.77
     Indore
    0.76
     validations
    0.75
    痠
    0.75
    使命
    0.73
     Rumania
    0.72
     cleanest
    0.71
    ৌ
    0.71
    Activations Density 0.007%

    No Known Activations