© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 13144
    Prev
    Next
    INDEX
    Explanations

    analogy comparison metaphor simile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    iesa
    0.40
    ")),
    0.39
    ंबा
    0.38
     Authentication
    0.35
     जानते
    0.35
     সম্মিলিত
    0.35
    ineri
    0.35
     உள்ப
    0.35
     अड
    0.34
    !("{:
    0.34
    POSITIVE LOGITS
     analogy
    2.63
     analogies
    2.55
     metaphor
    2.22
     comparison
    2.19
     comparisons
    2.14
     metaphors
    2.14
     срав
    2.06
     likened
    2.00
     porówn
    2.00
     simile
    1.98
    Activations Density 0.037%

    No Known Activations