© 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. 95712
    Prev
    Next
    INDEX
    Explanations

    equipped with kitchen or bathroom

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

    economic growth rates slowed recently

    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
    頔
    0.47
     Rook
    0.45
     Franciscan
    0.43
     নীরব
    0.43
     rook
    0.42
     Livestock
    0.42
     ومرحبا
    0.42
     దీ
    0.41
    枻
    0.41
     Holstein
    0.41
    POSITIVE LOGITS
    target
    0.50
    dinner
    0.49
    t
    0.49
    adjacent
    0.48
     serotonin
    0.47
    It
    0.47
    RBI
    0.47
    inim
    0.46
    0
    0.46
    ijen
    0.46
    Activations Density 0.002%

    No Known Activations