© 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. 31-GEMMASCOPE-2-RES-262K
    7. 74632
    Prev
    Next
    INDEX
    Explanations

    comparing things

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    0.71
    </h3>
    0.70
    </h1>
    0.68
    </th>
    0.62
     incremento
    0.61
    0.61
    0.59
     причине
    0.59
     représentants
    0.57
     emblematic
    0.57
    POSITIVE LOGITS
     Comparisons
    0.80
     сравни
    0.79
    比
    0.74
    .
    0.71
     comparison
    0.70
     비교
    0.69
     compare
    0.68
    Compar
    0.68
     तुलना
    0.68
     comparisons
    0.68
    Activations Density 0.032%

    No Known Activations