© 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. 56147
    Prev
    Next
    INDEX
    Explanations

    comparing unexpected events

    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
     سواء
    0.48
     ከአ
    0.45
    oglio
    0.44
     schnell
    0.43
     خواہ
    0.43
    하거나
    0.42
     شركات
    0.42
    忄
    0.42
     когда
    0.42
     그리스
    0.41
    POSITIVE LOGITS
    assertEquals
    0.44
     altru
    0.42
    haviours
    0.42
     enqueue
    0.41
     onsite
    0.40
     LIM
    0.39
     onwards
    0.39
     Sarawak
    0.39
     Ubud
    0.39
    ApiOperation
    0.39
    Activations Density 0.002%

    No Known Activations