© 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. 323
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    เท่า
    0.74
    B
    0.72
    บน
    0.65
    ซ
    0.64
     степени
    0.64
    。.
    0.63
    เนื่อง
    0.61
    ภายใน
    0.61
     B
    0.61
    ภาษา
    0.61
    POSITIVE LOGITS
     intends
    1.11
     expects
    1.08
     hasn
    1.07
     concedes
    1.03
     refuses
    1.02
     insists
    1.01
     believes
    1.00
     maintains
    1.00
     welcomes
    1.00
     wants
    0.99
    Activations Density 2.520%

    No Known Activations