© 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. 31-GEMMASCOPE-2-RES-262K
    7. 9880
    Prev
    Next
    INDEX
    Explanations

    categorized for clarity

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    （
    0.52
    ("
    0.47
    (
    0.45
     (>
    0.43
     (~
    0.43
     (<
    0.42
     শারীরিক
    0.41
     (
    0.40
    或
    0.40
     RP
    0.38
    POSITIVE LOGITS
     amoureux
    0.49
     aquel
    0.45
    ссажи
    0.44
     desafíos
    0.42
    стов
    0.42
     senhores
    0.41
    حب
    0.40
    ክ
    0.40
     ristrutt
    0.40
     успеха
    0.40
    Activations Density 0.127%

    No Known Activations