© 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. 5329
    Prev
    Next
    INDEX
    Explanations

    request permission or guidance

    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
    虜
    0.88
    ïdes
    0.84
     southernmost
    0.84
     sebanyak
    0.83
     vzd
    0.82
    اق
    0.81
     \"%
    0.81
     extremity
    0.80
     extremities
    0.80
    씹
    0.79
    POSITIVE LOGITS
    通常
    1.07
     important
    1.03
     usually
    1.01
     PIA
    0.96
     typically
    0.91
     Directive
    0.91
     Usually
    0.91
     Important
    0.90
    สำคัญ
    0.90
    허
    0.89
    Activations Density 0.000%

    No Known Activations