© 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. 205673
    Prev
    Next
    INDEX
    Explanations

    explaining something using "usually not"

    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
    pq
    0.42
     teste
    0.41
    毕竟
    0.41
    йы
    0.41
    ٹو
    0.40
    も
    0.40
     paiement
    0.40
    ۓ
    0.40
    plicates
    0.39
     zhōng
    0.39
    POSITIVE LOGITS
    kje
    0.41
    Conclusion
    0.41
    airy
    0.39
     molar
    0.39
    ammer
    0.39
                           
    0.38
    izophren
    0.38
    akor
    0.38
                               
    0.38
    ocious
    0.38
    Activations Density 0.002%

    No Known Activations