© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32964
    Prev
    Next
    INDEX
    Explanations

    taxonomic checklists and threatened species

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

    links and references in standardized scientific and software documentation formats.

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

    The neuron strongly activates on capitalized resource or publication names (e.g. database or journal titles and standardized lists) in reference and external‐links sections.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Not in Any Lists

    No Comments

    Negative Logits
    دارة
    -0.80
     funktion
    -0.76
     мыш
    -0.75
    SIZES
    -0.75
    硕士
    -0.75
    patients
    -0.74
     fonction
    -0.74
    nader
    -0.73
     Mujeres
    -0.73
     profit
    -0.73
    POSITIVE LOGITS
    lloworld
    1.03
     checklist
    1.02
     Checklist
    0.94
     taxonomic
    0.91
    階
    0.90
    owi
    0.88
    escence
    0.88
    fif
    0.84
    February
    0.84
     fifteenth
    0.82
    Activations Density 0.004%

    No Known Activations