© 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. 5199
    Prev
    Next
    INDEX
    Explanations

    favorite memory

    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
    ╽
    1.10
     島
    1.09
    氵
    1.08
    <unused1782>
    1.08
     방정식
    1.06
    ⢸
    1.05
    प्ताहिक
    1.03
    Unlocked
    1.01
    <unused314>
    1.00
     그림
    1.00
    POSITIVE LOGITS
     lol
    0.85
     flights
    0.85
     flying
    0.83
     records
    0.82
     fly
    0.82
     rares
    0.81
    会
    0.79
     el
    0.76
    si
    0.76
    ls
    0.74
    Activations Density 0.000%

    No Known Activations