© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 9817
    Prev
    Next
    INDEX
    Explanations

    pivotal in contemplation

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

    requests for and uses of metaphor-rich, figurative, high-register rhetorical language.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     (?)
    0.47
    /
    0.46
    ct
    0.45
    (?)
    0.45
     reproducing
    0.43
     able
    0.43
    :
    0.43
    z
    0.42
    いろいろ
    0.41
    txt
    0.41
    POSITIVE LOGITS
     desafíos
    0.60
     défis
    0.60
     reimag
    0.57
     unwavering
    0.56
     captivating
    0.56
    之际
    0.55
     चुनौतियों
    0.52
     desafios
    0.52
     സാഹ
    0.51
     cityscape
    0.51
    Activations Density 0.044%

    No Known Activations