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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7757
    Prev
    Next
    INDEX
    Explanations

    chiral molecules and chemistry

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

    The neuron is looking for scientific terms related to chirality and stereochemistry in chemical and physical contexts.

    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_10/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
    i
    -2.83
    c
    -2.75
    1
    -2.70
    p
    -2.53
    v
    -2.50
    ݯ
    -2.45
    .
    -2.44
    b
    -2.41
     маленьких
    -2.39
    n
    -2.38
    POSITIVE LOGITS
    蒟
    2.77
    OUTUBE
    2.56
    鲣
    2.31
    龊
    2.30
    سجيلات
    2.28
    霰
    2.22
    蜃
    2.14
    梟
    2.13
    😨
    2.11
    🫔
    2.11
    Activations Density 0.014%

    No Known Activations