© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4904
    Prev
    Next
    INDEX
    Explanations

    key responsibilities

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

    It detects section headings or phrases that mark the "responsibilities" part of job descriptions.

    oai_token-act-pair · gpt-5-mini
    Triggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    s
    0.93
    I
    0.89
    1
    0.82
    asing
    0.80
     a
    0.79
    \
    0.76
    【
    0.76
    houses
    0.76
    おい
    0.74
    alk
    0.74
    POSITIVE LOGITS
     be
    1.05
    ת
    1.04
    وية
    1.02
    ي
    1.02
    ul
    0.98
    ко
    0.94
    ু
    0.93
    ibilities
    0.92
    ות
    0.91
    ۔
    0.89
    Activations Density 0.005%

    No Known Activations