© 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. 2704
    Prev
    Next
    INDEX
    Explanations

    resources for help and support

    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_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
     也
    1.66
     assess
    1.66
     该
    1.63
     incite
    1.62
     port
    1.56
    스러운
    1.54
     グリーン
    1.52
     hastened
    1.52
     ござい
    1.52
     Anadolu
    1.50
    POSITIVE LOGITS
    どん
    1.47
    ेट्टी
    1.38
    बित
    1.30
    n
    1.27
     dobu
    1.26
    печа
    1.26
     théorie
    1.26
    écl
    1.25
    peč
    1.25
    今まで
    1.25
    Activations Density 0.072%

    No Known Activations