© 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. 224572
    Prev
    Next
    INDEX
    Explanations

    economic growth and investment

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

    origins and challenging 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
    惕
    0.50
    어졌
    0.45
    晰
    0.45
    萼
    0.45
    やっと
    0.44
    趼
    0.43
    溝
    0.42
    偐
    0.42
    越来越
    0.42
    以内
    0.42
    POSITIVE LOGITS
    lifts
    0.50
    toj
    0.50
    waste
    0.48
    rowth
    0.48
    wash
    0.48
    sectors
    0.48
    movement
    0.47
    neurons
    0.47
    reuses
    0.47
    attended
    0.47
    Activations Density 0.000%

    No Known Activations