© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3880
    Prev
    Next
    INDEX
    Explanations

    taught curriculum content

    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_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     endangering
    0.93
     undermine
    0.73
     undermining
    0.73
     வழி
    0.71
     mislead
    0.70
     привет
    0.70
    guess
    0.69
     endanger
    0.69
     punte
    0.69
    ::-
    0.68
    POSITIVE LOGITS
     taught
    1.55
    taught
    1.43
     teach
    1.35
     teaches
    1.31
     teaching
    1.23
    Teach
    1.18
    teach
    1.13
    teaching
    1.09
     Teach
    1.07
     Teaching
    1.07
    Activations Density 0.193%

    No Known Activations