© 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. 226525
    Prev
    Next
    INDEX
    Explanations

    song titles

    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
    ປະກ
    0.45
     આમંત્રણ
    0.44
     সারি
    0.44
    脐
    0.44
    舫
    0.41
     scripture
    0.40
     Assemblies
    0.40
     платфор
    0.40
    নীর
    0.40
     Scripture
    0.39
    POSITIVE LOGITS
     excellence
    0.42
     goa
    0.40
     dedi
    0.39
    ཧ
    0.39
     dedica
    0.39
     impro
    0.38
     Okada
    0.38
     PWR
    0.38
     haters
    0.38
     reworking
    0.38
    Activations Density 0.018%

    No Known Activations