© 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. 118013
    Prev
    Next
    INDEX
    Explanations

    university, student, wiki, promise

    np_acts-logits-general · gemini-2.5-flash-lite

    people compliment

    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
    0.59
    Cr
    0.52
    aced
    0.50
    ^
    0.48
    atsu
    0.47
    )
    0.47
    roduct
    0.46
    &
    0.46
    hem
    0.46
    {@
    0.45
    POSITIVE LOGITS
     університе
    0.64
     படை
    0.58
     жер
    0.55
     ویکی
    0.54
     інші
    0.53
    скі
    0.52
     aluno
    0.52
     ünivers
    0.52
     кото
    0.51
     уні
    0.50
    Activations Density 0.000%

    No Known Activations