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. 169
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by explanatory or instructional passages—phrases that introduce or break down concepts in a tutorial-style or detailed, step-by-step explanation.

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

    long, detailed explanatory or instructional passages (extended assistant-style responses).

    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
     a
    0.23
     of
    0.22
     
    0.22
     an
    0.22
     characteristics
    0.22
     coaxial
    0.22
     elegant
    0.22
     storage
    0.21
     the
    0.21
     casing
    0.21
    POSITIVE LOGITS
    ‌.
    0.35
    ۔
    0.34
    !!
    0.32
    ។
    0.32
    !.
    0.30
    !।
    0.30
    。
    0.30
    !
    0.29
     But
    0.29
     ۔
    0.29
    Activations Density 3.502%

    No Known Activations