© 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. 9697
    Prev
    Next
    INDEX
    Explanations

    those that describe

    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
     its
    0.44
    ختلف
    0.41
     uppermost
    0.39
     estão
    0.38
    üte
    0.38
     основных
    0.38
    pendicular
    0.38
     خود
    0.37
    odenum
    0.37
    3
    0.37
    POSITIVE LOGITS
     olyan
    0.93
    那些
    0.84
     situations
    0.80
     aquellos
    0.79
     those
    0.76
     ایسی
    0.73
    jenigen
    0.72
    คนที่
    0.72
     aqueles
    0.71
     những
    0.71
    Activations Density 0.231%

    No Known Activations