© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9298
    Prev
    Next
    INDEX
    Explanations

    fantastic and great affirmations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    の影響
    0.99
    слі
    0.93
     patchy
    0.92
     disastrous
    0.92
     déf
    0.90
     fiasco
    0.89
    影響
    0.88
    렵
    0.87
    히려
    0.87
     controversy
    0.87
    POSITIVE LOGITS
    你在
    1.26
    YOU
    1.21
     você
    1.20
    あなたが
    1.19
    来到
    1.19
     вами
    1.18
    あなた
    1.17
    走进
    1.15
     тебя
    1.14
    你有
    1.14
    Activations Density 0.239%

    No Known Activations