© 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. 480
    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
     tre
    0.58
     fre
    0.56
     bec
    0.56
     slav
    0.55
     insp
    0.54
     $:
    0.54
    spra
    0.53
     spar
    0.53
     genu
    0.52
     certa
    0.52
    POSITIVE LOGITS
     melakukan
    1.07
     meninggal
    1.04
    0
    1.00
     mengatakan
    0.96
     jumlah
    0.95
     melaksanakan
    0.95
    9
    0.94
    8
    0.94
     menyampaikan
    0.94
     menyatakan
    0.94
    Activations Density 0.708%

    No Known Activations