© 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. 48547
    Prev
    Next
    INDEX
    Explanations

    question / reaction

    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
    Fang
    0.48
    𝓂
    0.46
    yeah
    0.45
    Kuota
    0.44
    ⇝
    0.43
    Gang
    0.42
    മ
    0.42
    墮
    0.41
    Diego
    0.41
    engl
    0.41
    POSITIVE LOGITS
     importantly
    0.47
     in
    0.46
     vasta
    0.45
     coro
    0.44
     region
    0.44
     strany
    0.44
     nostru
    0.44
     însă
    0.43
     кор
    0.43
    コの
    0.43
    Activations Density 0.001%

    No Known Activations