© 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. 26370
    Prev
    Next
    INDEX
    Explanations

    racist and harmful content

    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
    '
    0.44
     Such
    0.42
    thus
    0.42
    那样
    0.41
     كذلك
    0.38
     thus
    0.38
     এভাবে
    0.38
    h
    0.38
    these
    0.38
     Easy
    0.37
    POSITIVE LOGITS
     nejen
    0.55
     ovviamente
    0.53
     굉장히
    0.52
     zarówno
    0.51
    のだが
    0.50
    んだけど
    0.49
    なのですが
    0.49
     tremendously
    0.48
    はもちろん
    0.46
     طبعا
    0.45
    Activations Density 0.011%

    No Known Activations