© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5419
    Prev
    Next
    INDEX
    Explanations

    ordinal and positional suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     पत्थर
    0.99
    TP
    0.98
     Hacer
    0.98
    عات
    0.95
    יש
    0.93
    eer
    0.93
    Кар
    0.90
    本
    0.90
    疹
    0.90
    杆
    0.89
    POSITIVE LOGITS
    most
    1.16
    anjutan
    1.03
    ittarius
    1.02
    驀
    0.98
    wards
    0.97
     backward
    0.96
    ward
    0.92
    seyside
    0.91
    तिर
    0.91
    footer
    0.91
    Activations Density 0.518%

    No Known Activations