© 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. 14312
    Prev
    Next
    INDEX
    Explanations

    narrow down best

    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_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
    жду
    1.61
    而在
    1.50
    在一
    1.46
    DER
    1.46
    ρ
    1.43
    жная
    1.40
    և
    1.37
    ებელი
    1.37
    ibbean
    1.35
    Ϊ
    1.35
    POSITIVE LOGITS
     simpel
    1.74
     minta
    1.72
     pusat
    1.72
     hukuk
    1.71
     utama
    1.65
     marah
    1.65
     scegli
    1.64
     soz
    1.64
     naturali
    1.63
     tradisional
    1.59
    Activations Density 0.161%

    No Known Activations