© 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. 2604
    Prev
    Next
    INDEX
    Explanations

    color and code

    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
    kj
    1.05
    kB
    1.01
    kD
    0.96
    k
    0.84
     Packard
    0.82
    동안
    0.81
    btnClear
    0.81
    kJ
    0.80
     roadblocks
    0.80
    Np
    0.79
    POSITIVE LOGITS
     вер
    1.09
     प्रमेय
    1.03
     يَ
    1.03
     НЕ
    1.02
     Сан
    1.01
     Вер
    1.01
     י
    1.00
    consistency
    0.98
    variance
    0.98
    夆
    0.98
    Activations Density 0.043%

    No Known Activations