© 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. 309
    Prev
    Next
    INDEX
    Explanations

    Romantic Era texts

    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
    ة
    1.77
    es
    1.75
     هیڅ
    1.61
     کوم
    1.56
    isIn
    1.55
    nya
    1.52
    ట్లో
    1.51
    ्याय
    1.48
    nested
    1.46
    Литература
    1.44
    POSITIVE LOGITS
     lắc
    1.77
    bral
    1.74
    quate
    1.68
    ciplinary
    1.64
    webkit
    1.61
    劲
    1.60
     hòa
    1.60
     vong
    1.60
    בד
    1.60
    不了
    1.59
    Activations Density 0.000%

    No Known Activations