© 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-65K
    7. 2016
    Prev
    Next
    INDEX
    Explanations

    matter of faith

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     말투
    0.68
    قتصاد
    0.62
    ્વાસ
    0.60
     Notation
    0.58
     moviment
    0.57
     Inference
    0.57
     huid
    0.57
     labb
    0.56
    प्रयोग
    0.56
    簷
    0.56
    POSITIVE LOGITS
     spiritual
    1.92
    spiritual
    1.65
     Spiritual
    1.52
     spirituality
    1.43
     transcendent
    1.41
     espiritual
    1.41
     transcendental
    1.40
     divine
    1.37
     духов
    1.37
     innate
    1.37
    Activations Density 1.294%

    No Known Activations