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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109755
    Prev
    Next
    INDEX
    Explanations

    words like Hydra or Lacy Jr

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

    This neuron activates on names of chemical compounds, medical terms, and scientific terminology, particularly those with 'hy' or 'hyd' prefixes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     nightfall
    -0.81
    ’;
    -0.80
    luri
    -0.79
     פון
    -0.77
    餘
    -0.77
     کره
    -0.75
     canale
    -0.74
    Detailed
    -0.74
    remmo
    -0.73
    rophoto
    -0.73
    POSITIVE LOGITS
    羡
    0.77
    Dys
    0.75
    之家
    0.74
    sspiel
    0.73
    愉
    0.73
    THRESH
    0.72
    niet
    0.72
     วัน
    0.71
    端的
    0.71
     primacy
    0.70
    Activations Density 0.023%

    No Known Activations