© 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. 137756
    Prev
    Next
    INDEX
    Explanations

    Power Delivery, Relation Extraction, Cloud Services

    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
     vingt
    0.39
    rosa
    0.38
    steil
    0.38
    UnderTest
    0.38
    촘
    0.36
     चली
    0.36
    ிக
    0.36
     we
    0.36
    Location
    0.36
    offsetLeft
    0.36
    POSITIVE LOGITS
     MDS
    0.40
     BDS
    0.39
    ufact
    0.38
    >∕
    0.37
     PUC
    0.37
    emento
    0.36
     NASCAR
    0.36
     excavator
    0.36
    émico
    0.36
    assign
    0.36
    Activations Density 0.000%

    No Known Activations