© 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. 270
    Prev
    Next
    INDEX
    Explanations

    rhesus macaques

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

    scientific names of primate species, particularly macaques.

    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
    ʦ
    -0.74
    プーン
    -0.69
     삼
    -0.67
    ার্
    -0.67
    finger
    -0.66
    それと
    -0.66
    Capa
    -0.65
     Bertie
    -0.65
     आदि
    -0.65
    حيان
    -0.65
    POSITIVE LOGITS
     olive
    0.91
     maca
    0.81
     cheek
    0.81
    ServiceProvider
    0.79
     Olive
    0.79
     cyn
    0.79
    VISION
    0.76
     colorectal
    0.76
    음
    0.75
    geen
    0.75
    Activations Density 0.069%

    No Known Activations