© 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. 41-GEMMASCOPE-2-RES-262K
    7. 35303
    Prev
    Next
    INDEX
    Explanations

    star burning fuel

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Cast
    0.44
    CAST
    0.42
     Cast
    0.41
     संय
    0.41
    caster
    0.40
     गुन
    0.40
     সিরাপ
    0.39
     baixar
    0.39
    ﻛ
    0.39
    锁定
    0.39
    POSITIVE LOGITS
     outward
    0.65
     hydrostatic
    0.59
     pressures
    0.52
     Hydro
    0.52
     outwards
    0.52
     inward
    0.50
     Burning
    0.49
     pressure
    0.46
     Pressure
    0.46
     burns
    0.45
    Activations Density 0.003%

    No Known Activations