© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 225872
    Prev
    Next
    INDEX
    Explanations

    contrastive or additive discourse connectors that signal a shift or qualification within a sentence.

    oai_token-act-pair · gpt-5
    Triggered 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
    Negative Logits
     necrosis
    0.48
     decolor
    0.47
    ꯟ
    0.46
    <0x9B>
    0.46
     delicacies
    0.45
    ᅴ
    0.45
    graphHead
    0.44
     flooding
    0.44
     respiration
    0.43
    apoptotic
    0.42
    POSITIVE LOGITS
    k
    0.53
    不在
    0.48
    t
    0.47
     Lihat
    0.46
    l
    0.45
    ψη
    0.44
    te
    0.43
     olmay
    0.43
     jangan
    0.42
     Kandid
    0.42
    Activations Density 0.012%

    No Known Activations