© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 233844
    Prev
    Next
    INDEX
    Explanations

    producing or explaining preceding concepts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ada
    0.57
    path
    0.56
    its
    0.54
    it
    0.53
    await
    0.52
    os
    0.52
    xious
    0.52
    0
    0.51
    1
    0.50
    as
    0.50
    POSITIVE LOGITS
     incest
    0.56
     onscreen
    0.49
     zom
    0.48
     equine
    0.47
     бизнеса
    0.46
     agribusiness
    0.46
     extortion
    0.46
     svim
    0.46
     unopened
    0.46
     prostitution
    0.45
    Activations Density 0.000%

    No Known Activations