© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2580
    Prev
    Next
    INDEX
    Explanations

    past participles after "ve"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     been
    1.64
    𝘦
    1.64
    𝘯
    1.62
    𝘶
    1.56
     nevoie
    1.54
    𝘰
    1.48
     begun
    1.47
    /−
    1.47
    𝘢
    1.45
     blitt
    1.42
    POSITIVE LOGITS
    v
    1.66
    rifice
    1.65
    et
    1.63
     daraus
    1.59
    ση
    1.59
    ตรฐาน
    1.52
    न
    1.45
    zien
    1.34
    le
    1.34
     производи
    1.33
    Activations Density 0.079%

    No Known Activations