© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 8898
    Prev
    Next
    INDEX
    Explanations

    set /p choice

    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
    isely
    1.37
    áciu
    1.35
     radially
    1.29
     Astron
    1.27
     calibrated
    1.26
     👉
    1.25
    ofSeconds
    1.25
    etrically
    1.25
     딱
    1.24
    六年
    1.24
    POSITIVE LOGITS
     ребенок
    0.94
     voud
    0.90
     фе
    0.87
     sickness
    0.87
    入
    0.86
     vend
    0.86
    进了
    0.85
     poisons
    0.84
    したが
    0.84
     sue
    0.83
    Activations Density 0.000%

    No Known Activations