© 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-65K
    7. 61139
    Prev
    Next
    INDEX
    Explanations

    Primarily platforms and products

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    危险
    0.56
    危机
    0.53
     અને
    0.53
     ਅਤੇ
    0.50
     এবং
    0.50
     и
    0.50
    下来的
    0.50
     उनके
    0.48
     кандида
    0.48
    导致的
    0.48
    POSITIVE LOGITS
    9
    0.55
    5
    0.48
     three
    0.48
     like
    0.46
    t
    0.46
    x
    0.46
    6
    0.46
     Pizza
    0.46
     selama
    0.45
     periods
    0.45
    Activations Density 0.009%

    No Known Activations