© 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. 5962
    Prev
    Next
    INDEX
    Explanations

    driven by desire

    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
     Aluminium
    0.75
    crate
    0.73
    er
    0.73
    铝
    0.73
     многое
    0.73
     aluminum
    0.72
     breathable
    0.72
    itakan
    0.72
    Aluminum
    0.70
     impug
    0.69
    POSITIVE LOGITS
     insanity
    0.88
    Claud
    0.81
     ശക്ത
    0.77
     다만
    0.77
     unsound
    0.75
    ៈ
    0.75
     menjual
    0.72
     insane
    0.69
     جامع
    0.69
     Bxd
    0.69
    Activations Density 0.009%

    No Known Activations