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. 89
    Prev
    Next
    INDEX
    Explanations

    the neuron fires on blocks of natural-language explanation (prose commentary), as opposed to code tokens.

    oai_token-act-pair · o4-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
    -
    0.41
     which
    0.38
     ως
    0.38
    <sup>
    0.36
     -
    0.36
    .
    0.35
     framework
    0.34
     versus
    0.34
     regions
    0.34
     மற்றும்
    0.34
    POSITIVE LOGITS
     Paise
    0.42
    Não
    0.41
    Tidak
    0.40
     দেরী
    0.40
    nicht
    0.39
    誑
    0.39
    တတ်
    0.38
    VerFile
    0.38
     Probleme
    0.38
    tidak
    0.38
    Activations Density 0.000%

    No Known Activations