© 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. 1700
    Prev
    Next
    INDEX
    Explanations

    Japanese and Chinese poetry and art

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

    Chinese poetry and river

    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
    鋅
    0.87
    髖
    0.85
    劊
    0.83
    閆
    0.83
    證據
    0.82
    詆
    0.82
    ॉम
    0.81
    銠
    0.79
    銨
    0.79
    鉭
    0.79
    POSITIVE LOGITS
     poetry
    1.06
     poems
    1.00
     Poetry
    0.98
     poetic
    0.98
     poem
    0.96
     poets
    0.92
     poet
    0.91
     flower
    0.88
     Poet
    0.82
     poeta
    0.80
    Activations Density 0.055%

    No Known Activations