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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 20363
    Prev
    Next
    INDEX
    Explanations

    narrative concepts or factual descriptions

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

    the neuron responds to technical or scientific content—terms, measurements, and data-heavy/highly specific words found in experimental or domain-specific descriptions.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
    i
    0.55
    c
    0.52
    n
    0.50
    d
    0.50
    g
    0.50
    0
    0.49
    im
    0.47
    ন
    0.47
    r
    0.46
    id
    0.46
    POSITIVE LOGITS
     약간
    0.48
     fable
    0.47
     paramet
    0.46
     ሁለት
    0.45
     ఒక
    0.45
     Änderung
    0.44
     disgraceful
    0.44
     parable
    0.44
     dictum
    0.44
     epiphany
    0.44
    Activations Density 0.038%

    No Known Activations