© 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. 36697
    Prev
    Next
    INDEX
    Explanations

    electronic circuits and components

    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
     खपत
    0.43
    遷移
    0.42
    邺
    0.38
    lava
    0.37
    기업
    0.37
    らん
    0.36
    spine
    0.36
     Spine
    0.36
    ͹
    0.35
     maest
    0.35
    POSITIVE LOGITS
     detector
    0.86
     comparator
    0.83
     discriminator
    0.81
     Comparator
    0.75
     demod
    0.75
     circuits
    0.74
    Detector
    0.74
     amplifier
    0.73
     detectors
    0.73
     amplifiers
    0.72
    Activations Density 0.018%

    No Known Activations