© 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. 9218
    Prev
    Next
    INDEX
    Explanations

    usually benign or normal

    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
    ᕇ
    0.52
     अनुश
    0.48
    Ин
    0.44
    Estate
    0.44
    憲
    0.44
    𝙵
    0.44
    शन
    0.43
    estate
    0.43
    avgsalary
    0.43
    ৩৫
    0.42
    POSITIVE LOGITS
     come
    0.54
     causes
    0.51
     simple
    0.46
     initiate
    0.46
     predictable
    0.45
     arises
    0.44
     bought
    0.44
     (
    0.44
     arise
    0.44
     spontaneous
    0.44
    Activations Density 0.026%

    No Known Activations