© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6702
    Prev
    Next
    INDEX
    Explanations

    et al. citation author lists

    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_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Stockton
    0.65
     blueprints
    0.63
    굴
    0.62
     contracted
    0.62
     Popper
    0.61
     readline
    0.59
     legislative
    0.59
     legislation
    0.58
    ἱ
    0.57
     Nightingale
    0.56
    POSITIVE LOGITS
     et
    1.25
     الخ
    0.83
     Email
    0.82
    化妆
    0.81
     oben
    0.80
    argmin
    0.79
     Et
    0.79
     उपरोक्त
    0.76
     email
    0.74
     عزی
    0.74
    Activations Density 0.049%

    No Known Activations