© 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. 22-GEMMASCOPE-2-RES-16K
    7. 640
    Prev
    Next
    INDEX
    Explanations

    actions and instructions

    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_22_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
     bukanlah
    1.08
    其實
    1.07
     adalah
    1.04
    虽
    1.03
    其实
    1.01
    应该是
    1.00
     była
    1.00
     był
    0.98
     provient
    0.98
     merupakan
    0.98
    POSITIVE LOGITS
     رفع
    1.38
    挑
    1.20
     đánh
    1.17
     جذب
    1.15
    จัด
    1.12
     تش
    1.11
     mettre
    1.11
     تح
    1.11
     تس
    1.09
     보내
    1.09
    Activations Density 0.104%

    No Known Activations