© 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-262K
    7. 26368
    Prev
    Next
    INDEX
    Explanations

    Smart HDR

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    erer
    0.42
     visitation
    0.41
     suporte
    0.40
    步驟
    0.38
    ன்னி
    0.37
    executor
    0.37
     основу
    0.37
    ]:
    0.36
    श्मीर
    0.36
     Palestine
    0.36
    POSITIVE LOGITS
    众
    0.46
    Jamie
    0.39
    SUM
    0.39
    Wor
    0.38
     '%
    0.38
    Une
    0.38
     Homestead
    0.38
    쟁
    0.38
     Jamie
    0.38
    Raise
    0.37
    Activations Density 0.000%

    No Known Activations