© 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. 71773
    Prev
    Next
    INDEX
    Explanations

    genes related to organisms

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

    The neuron identifies animal and plant species names, especially in scientific/biological 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
     they
    -1.71
    。『
    -1.38
     делает
    -1.36
    苼
    -1.31
     moeten
    -1.30
    ᵈ
    -1.29
    ꙰
    -1.26
    tabPage
    -1.24
     christlichen
    -1.24
     Mereka
    -1.23
    POSITIVE LOGITS
     with
    1.55
     When
    1.47
     specific
    1.34
     While
    1.33
    szönöm
    1.31
     bereits
    1.31
    Both
    1.30
    кота
    1.27
     Although
    1.27
     тис
    1.25
    Activations Density 0.448%

    No Known Activations