© 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-16K
    7. 7699
    Prev
    Next
    INDEX
    Explanations

    maximum size or limit

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    formatted
    0.41
     निर्देशा
    0.40
    缺少
    0.40
     unrestricted
    0.40
    status
    0.40
    Formatted
    0.40
    ⏜
    0.39
    LaunchAction
    0.39
     አይደለም
    0.38
     Официа
    0.38
    POSITIVE LOGITS
     threshold
    0.80
     Threshold
    0.72
     maximum
    0.66
    Threshold
    0.65
    threshold
    0.65
     tolerance
    0.63
     thresholds
    0.61
     radius
    0.61
     maxLength
    0.59
    阈
    0.59
    Activations Density 0.278%

    No Known Activations