© 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-TRANSCODER-262K
    7. 19130
    Prev
    Next
    INDEX
    Explanations

    fight, race, battle, pursuit, search against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    மையில்
    0.40
     Übers
    0.38
     FUR
    0.38
     Companion
    0.37
    ंक
    0.37
     pleno
    0.36
     CSM
    0.36
    ॢ
    0.36
    ้าว
    0.35
     tartış
    0.35
    POSITIVE LOGITS
     against
    0.92
    against
    0.91
     Against
    0.86
    Against
    0.81
     против
    0.80
     gegen
    0.79
     ضد
    0.77
     AGAINST
    0.72
     tegen
    0.71
     contre
    0.65
    Activations Density 0.066%

    No Known Activations