© 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. 40-GEMMASCOPE-2-RES-16K
    7. 7858
    Prev
    Next
    INDEX
    Explanations

    `<UNK>`, `<HUMAN>`, `<image>`, `<math>`

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     indiquer
    0.45
     Accesat
    0.44
     referenties
    0.42
     Senhor
    0.41
     tenido
    0.40
    aderas
    0.40
    的表现
    0.40
    槛
    0.40
    \";
    0.39
     sobrevivir
    0.39
    POSITIVE LOGITS
    ...>
    0.71
    br
    0.49
    Moment
    0.45
    >()
    0.43
    priority
    0.43
    .>
    0.43
    jasmine
    0.41
    ิร์
    0.41
     `<=
    0.41
    ບບ
    0.40
    Activations Density 0.076%

    No Known Activations