© 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. 141162
    Prev
    Next
    INDEX
    Explanations

    physician, commissioner, tells, resistance

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

    However, adding complexity

    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
     अर्जेंटीना
    0.46
     feb
    0.45
     decre
    0.45
     ottoman
    0.44
     JET
    0.44
     Nino
    0.43
     Argentine
    0.43
     torrential
    0.43
     Argentina
    0.42
    ಔ
    0.41
    POSITIVE LOGITS
    э
    0.52
    localScale
    0.44
    妘
    0.43
    獾
    0.43
    实际
    0.43
    搞
    0.42
    ̥
    0.42
    ные
    0.41
     сочи
    0.41
     э
    0.41
    Activations Density 0.000%

    No Known Activations