© 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. 42131
    Prev
    Next
    INDEX
    Explanations

    console.info, investigated, minutes, priorities, hidden, IDs

    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
    un
    0.47
    on
    0.44
    оз
    0.43
    т
    0.42
    佑
    0.41
    ље
    0.41
     Tory
    0.41
     hiểm
    0.41
    unsafe
    0.40
    UN
    0.40
    POSITIVE LOGITS
    ッキリ
    0.53
     پاکستانی
    0.50
     청바
    0.50
     সদ্য
    0.49
     yks
    0.49
     ストレ
    0.48
    ien
    0.47
     売
    0.47
    ಬಹುದ
    0.47
     liners
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.