© 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. 75619
    Prev
    Next
    INDEX
    Explanations

    generating code and SDKs

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

    generate code or interfaces

    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
     acidosis
    0.52
    ዷ
    0.45
     dyed
    0.43
    шивания
    0.42
    acha
    0.41
    istasis
    0.41
     Bacteriol
    0.40
    🏔
    0.40
     mesons
    0.40
    emorrh
    0.39
    POSITIVE LOGITS
    生成
    0.82
     Generate
    0.78
     generating
    0.75
    生成的
    0.74
    Generate
    0.73
     Generated
    0.73
     Generating
    0.72
    Generating
    0.71
     generate
    0.69
     generated
    0.68
    Activations Density 0.055%

    No Known Activations