Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-16K
    4. 515
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on specific plant variety (cultivar) names in lists.

    oai_token-act-pair · o4-miniTriggered by @camilab

    The neuron detects named-entity tokens — proper names and titles (e.g., cultivar/variety names, people, album or work names) often used as headings or list items.

    oai_token-act-pair · gpt-5-miniTriggered by @camilab
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     frugal
    0.25
     adverb
    0.23
     factual
    0.23
     inextric
    0.23
     objectionable
    0.22
     subjekt
    0.22
     отсутствии
    0.22
     entendimento
    0.22
     postulate
    0.22
    обходи
    0.22
    POSITIVE LOGITS
    P
    0.31
    M
    0.31
    、
    0.31
    an
    0.30
    ia
    0.29
    al
    0.29
    T
    0.28
    ar
    0.27
    H
    0.27
     ಮತ್ತು
    0.27
    Activations Density 12.897%

    No Known Activations