© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5246
    Prev
    Next
    INDEX
    Explanations

    error and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     human
    1.24
    కు
    1.22
    异常
    1.18
    tes
    1.15
    cpf
    1.15
     unfriendly
    1.14
    κών
    1.14
     Human
    1.12
    서
    1.11
    t
    1.09
    POSITIVE LOGITS
     glycolysis
    1.48
    intermediate
    1.42
    ظيم
    1.40
    蛳
    1.40
    izont
    1.38
    烀
    1.38
    रोज
    1.37
     melakukannya
    1.36
    ंगाबाद
    1.34
     castings
    1.32
    Activations Density 0.066%

    No Known Activations