© 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. 2868
    Prev
    Next
    INDEX
    Explanations

    sensitive topics like exploitation

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

    The neuron detects safety- and instruction-oriented text—urgent warnings, safety headings, and imperative/advisory guidance.

    oai_token-act-pair · gpt-5-mini
    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
     сыгра
    0.40
    enz
    0.37
    Division
    0.36
    InputChange
    0.36
    ﹀
    0.36
    ণিজ
    0.35
    supporting
    0.35
    Changes
    0.34
    rások
    0.34
    ref
    0.34
    POSITIVE LOGITS
    忙
    0.57
     delicate
    0.55
     fragile
    0.53
     crowded
    0.52
     busy
    0.52
     sensitive
    0.51
     sedang
    0.50
     ऑलरेडी
    0.50
     hectic
    0.49
     unsuspecting
    0.49
    Activations Density 0.157%

    No Known Activations