© 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. 3849
    Prev
    Next
    INDEX
    Explanations

    specialized or comparative contexts

    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
     atof
    0.70
    
    0.67
     चव्हाण
    0.66
     Bapak
    0.66
    对照
    0.65
     affirmed
    0.65
    ঞ
    0.64
    ŏ
    0.63
     affirms
    0.63
    opyran
    0.62
    POSITIVE LOGITS
     specialized
    1.74
     specialised
    1.70
     Specialized
    1.60
     specialty
    1.52
     rarer
    1.50
     special
    1.49
     специализирован
    1.49
     speciality
    1.45
     newer
    1.44
    Special
    1.42
    Activations Density 1.490%

    No Known Activations