© 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. 85332
    Prev
    Next
    INDEX
    Explanations

    in or on ingredients

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

    modern/traditional comparison

    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
    Between
    0.51
    і
    0.50
    Against
    0.48
     on
    0.48
    InData
    0.47
    payers
    0.45
    不僅
    0.44
     отказыва
    0.42
     нужно
    0.42
    ї
    0.42
    POSITIVE LOGITS
     interleukin
    0.53
    ASY
    0.50
     cytosol
    0.50
     aspirin
    0.49
     ác
    0.49
     selatan
    0.49
     ATPase
    0.48
     mannitol
    0.48
     unstable
    0.48
     ripening
    0.48
    Activations Density 0.001%

    No Known Activations