© 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. 40-GEMMASCOPE-2-RES-262K
    7. 130094
    Prev
    Next
    INDEX
    Explanations

    Australian box jellyfish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     inject
    0.42
    <0xB2>
    0.42
    Inject
    0.42
     अधिवक्ता
    0.41
     injection
    0.40
    洴
    0.40
     tend
    0.39
     ㅁ
    0.39
     রাজধান
    0.39
     injections
    0.38
    POSITIVE LOGITS
    rels
    0.40
    Johnson
    0.38
    trading
    0.38
     бух
    0.37
    poz
    0.36
    hour
    0.36
    正面
    0.36
    ރ
    0.36
     Gegen
    0.35
     unfriendly
    0.35
    Activations Density 0.001%

    No Known Activations