© 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. 31-GEMMASCOPE-2-RES-262K
    7. 107978
    Prev
    Next
    INDEX
    Explanations

    emphasize or stress importance

    np_acts-logits-general · gemini-2.5-flash-lite

    emphasize or importance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    k
    0.83
    sp
    0.82
    ल
    0.72
    m
    0.67
    ä
    0.66
    f
    0.66
    sm
    0.64
     भास्कर
    0.64
    $)
    0.63
    ästä
    0.62
    POSITIVE LOGITS
    强调
    1.16
    強調
    1.09
     emphasize
    1.05
     emphasizes
    1.01
     emphasized
    0.98
     강조
    0.96
     vurg
    0.93
     emphasise
    0.93
     emphasised
    0.91
     betont
    0.91
    Activations Density 0.079%

    No Known Activations