© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129751
    Prev
    Next
    INDEX
    Explanations

    adopted Federation guidelines

    np_acts-logits-general · gemini-2.5-flash-lite

    pretend, clear, why, that, right, consistently, focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ト
    0.50
    カナ
    0.42
     evolve
    0.41
     extranjeros
    0.40
    mathspace
    0.39
     astronomers
    0.37
     と
    0.36
     deviation
    0.36
     evolves
    0.36
     originates
    0.35
    POSITIVE LOGITS
    ৮
    0.49
    鬃
    0.48
     Preservation
    0.47
    劲
    0.46
    腰
    0.46
     Campbell
    0.46
     unmittelbar
    0.46
     progetti
    0.45
    长期
    0.44
    承诺
    0.44
    Activations Density 0.001%

    No Known Activations