© 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. 132906
    Prev
    Next
    INDEX
    Explanations

    popular topicsshowing topic

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

    quantities, conditions, factors

    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
     Stadt
    0.49
    -
    0.49
     Factory
    0.48
     Toolkit
    0.46
    针对
    0.46
    0.45
     Package
    0.45
     Trainer
    0.45
    čných
    0.45
     Program
    0.45
    POSITIVE LOGITS
     legumes
    0.49
    𒌆
    0.47
     कॉनक
    0.47
    excluding
    0.46
     perils
    0.46
    ヨ
    0.46
     adversaries
    0.46
     worsened
    0.46
    ು
    0.45
     フラワー
    0.45
    Activations Density 0.001%

    No Known Activations