© 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. 2306
    Prev
    Next
    INDEX
    Explanations

    negative numbers and operations

    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_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
    กิน
    0.52
    Imidazole
    0.52
    मॉडल
    0.52
    കളിൽ
    0.48
    म्यान
    0.48
    ina
    0.47
    این
    0.47
    ighthouse
    0.47
    ם
    0.47
    Historia
    0.47
    POSITIVE LOGITS
     (-)
    0.83
     (-
    0.77
     negative
    0.73
     (−
    0.72
     $(-
    0.68
    (-
    0.63
     отрица
    0.61
     negatives
    0.60
    negative
    0.59
    }=-
    0.59
    Activations Density 0.103%

    No Known Activations