© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112109
    Prev
    Next
    INDEX
    Explanations

    phage display or bootloader operations

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

    words related to specific technical or specialized terms, particularly in scientific, medical, and programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on uncommon, domain-specific jargon or proper‐nouns and technical terms.

    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
    .
    -2.98
    Every
    -2.73
     or
    -2.70
     pushes
    -2.59
     facilitates
    -2.55
    For
    -2.42
    Sometimes
    -2.42
    and
    -2.41
    one
    -2.38
    Both
    -2.34
    POSITIVE LOGITS
     delightfully
    3.45
     deliciously
    3.23
    臯
    2.94
     wonderfully
    2.88
     nonchal
    2.86
     unbelievably
    2.86
     AMAZING
    2.81
     REALLY
    2.78
     bizarre
    2.78
     ridiculously
    2.64
    Activations Density 0.007%

    No Known Activations