© 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. 219
    Prev
    Next
    INDEX
    Explanations

    National crisis hotlines

    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
     с
    0.63
    typen
    0.63
    slightly
    0.62
    modulo
    0.61
    ОВ
    0.61
    thick
    0.61
    silhouette
    0.60
    encoding
    0.60
    ბ
    0.60
    metast
    0.58
    POSITIVE LOGITS
     diadakan
    0.88
     berlangsung
    0.82
     جمہوری
    0.81
    ズノ
    0.80
    JlcG
    0.80
     タイヤ
    0.80
    szág
    0.79
     アルミ
    0.78
    Issledovatel
    0.78
     yapılacak
    0.77
    Activations Density 1.408%

    No Known Activations