© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3582
    Prev
    Next
    INDEX
    Explanations

    natriuretic peptides and related names

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

    syllables or characters that appear in names, particularly detecting parts of proper names like "ri" in various contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    นั้น
    -0.82
    бовь
    -0.77
    <=
    -0.75
     ==========
    -0.74
     mostly
    -0.74
    脸
    -0.68
    past
    -0.68
     surely
    -0.68
    Within
    -0.68
     totally
    -0.67
    POSITIVE LOGITS
     warts
    0.82
    фраструк
    0.81
     configurable
    0.80
     dalších
    0.78
    riges
    0.77
     Vri
    0.77
    PRI
    0.74
    oderma
    0.73
    кобрита
    0.73
    dictions
    0.73
    Activations Density 0.105%

    No Known Activations