© 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. 836
    Prev
    Next
    INDEX
    Explanations

    determining viability

    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
    個人
    1.09
     notificações
    1.06
    称号
    1.05
    不斷
    1.01
    不做
    1.00
     alerts
    0.98
     cercano
    0.97
    鼾
    0.96
    他の
    0.96
    不论
    0.96
    POSITIVE LOGITS
    necessarily
    1.38
     necessarily
    1.33
     voldoende
    1.30
    optimal
    1.26
     hề
    1.24
     enough
    1.22
     đủ
    1.19
     suficient
    1.19
     adequ
    1.17
     adequate
    1.16
    Activations Density 1.143%

    No Known Activations