© 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. 7-GEMMASCOPE-2-RES-16K
    7. 381
    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_7_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
     $>$
    1.06
     반지름
    1.05
     ['',
    1.03
     ١
    1.03
     ٣
    1.02
     ٢
    1.02
     $)$
    1.00
     दूस
    1.00
     Нет
    0.98
     yönt
    0.98
    POSITIVE LOGITS
    th
    1.36
    0
    1.33
    ⃣
    1.18
    ″
    1.17
    9
    1.13
    ️⃣
    1.12
    7
    1.11
    5
    1.07
    s
    1.06
    ′
    1.03
    Activations Density 4.354%

    No Known Activations