© 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-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 833
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     և
    0.78
     be
    0.74
     can
    0.70
    </h5>
    0.66
     was
    0.66
    }.
    0.66
     vicepresidente
    0.66
     որ
    0.66
     ка
    0.65
     și
    0.65
    POSITIVE LOGITS
    f
    0.91
    i
    0.72
    ב
    0.70
    ار
    0.69
    k
    0.67
    मैन
    0.66
    problems
    0.65
    hā
    0.65
    ㅋ
    0.64
    ह
    0.63
    Activations Density 4.819%

    No Known Activations