© 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. 5969
    Prev
    Next
    INDEX
    Explanations

    been followed by actions

    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
    sterile
    0.71
    なります
    0.67
    _(
    0.67
     now
    0.66
    ；
    0.64
    Yet
    0.64
    still
    0.63
     ？
    0.63
    成了
    0.61
    _,
    0.61
    POSITIVE LOGITS
    nid
    0.84
    ఞ
    0.84
     Unpublished
    0.82
     broadcasting
    0.81
    ល្អ
    0.81
    <unused1124>
    0.81
    mike
    0.79
    tke
    0.79
     looping
    0.78
    လုံး
    0.77
    Activations Density 0.112%

    No Known Activations