© 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. 7181
    Prev
    Next
    INDEX
    Explanations

    `/]( sequence in URLs

    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
     त्याच
    0.97
     खासकर
    0.96
    --“
    0.95
     فريبيس
    0.94
    κες
    0.94
    (“
    0.93
     वेगवेगळ्या
    0.93
    ίες
    0.92
     könnten
    0.91
    odeon
    0.91
    POSITIVE LOGITS
     gram
    0.88
    》。
    0.86
    pr
    0.82
     psych
    0.82
    l
    0.79
     Br
    0.79
     rå
    0.79
    col
    0.79
     Vish
    0.79
    vard
    0.78
    Activations Density 0.004%

    No Known Activations