© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9264
    Prev
    Next
    INDEX
    Explanations

    single crystal mutations

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

    scientific terms related to genetics, particularly the phrase "germ line" and "single crystal".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly fires on the exact token “line” (e.g. in “germ line,” “cancer germ line,” “germ-line stem cells,” or any standalone “line”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ">
    
    -1.85
    -1.83
     с
    -1.61
     are
    -1.59
     verschiedene
    -1.56
    ();
    
    -1.55
     в
    -1.53
     {
    
    -1.52
    f
    -1.51
    >
    
    -1.49
    POSITIVE LOGITS
    これらの
    1.57
     only
    1.55
    一枚
    1.48
     někdo
    1.46
     of
    1.45
    這些
    1.45
     jų
    1.43
     musíte
    1.42
     těchto
    1.41
     dichos
    1.39
    Activations Density 0.041%

    No Known Activations