© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2821
    Prev
    Next
    INDEX
    Explanations

    internal code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     sosyal
    0.86
     Möglichkeiten
    0.84
     Miley
    0.83
     soziale
    0.80
    recyclerView
    0.78
     Passenger
    0.76
     Cola
    0.76
     Tourism
    0.75
    㐱
    0.74
    Tourism
    0.74
    POSITIVE LOGITS
     introspection
    0.80
     hidden
    0.75
     internal
    0.75
    iless
    0.74
     harden
    0.73
    debug
    0.73
    रासत
    0.71
     invariant
    0.71
     atoms
    0.70
    introspection
    0.69
    Activations Density 0.851%

    No Known Activations