© 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. 17-GEMMASCOPE-2-RES-16K
    7. 5910
    Prev
    Next
    INDEX
    Explanations

    y coordinate

    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_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     both
    0.64
    αιο
    0.63
     facts
    0.59
     પ્રે
    0.58
    未満
    0.56
     either
    0.55
     neither
    0.55
    하여
    0.54
     fact
    0.53
     *
    0.51
    POSITIVE LOGITS
     Y
    1.38
    Y
    1.34
     y
    1.32
     VPN
    1.02
    YZ
    1.01
    Yvette
    1.01
     Ond
    1.00
     Yor
    1.00
     getY
    0.99
    Yu
    0.99
    Activations Density 0.085%

    No Known Activations