© 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. 16156
    Prev
    Next
    INDEX
    Explanations

    somewhat X or rather than Y

    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
    vať
    1.69
    elves
    1.59
    Архівовано
    1.59
    jte
    1.55
    ల
    1.51
    utsu
    1.48
    penas
    1.48
    壤
    1.47
    at
    1.47
    ње
    1.46
    POSITIVE LOGITS
     sigui
    1.88
     multe
    1.76
     decât
    1.74
     всего
    1.69
     consumed
    1.64
     exceed
    1.61
    ઉસ
    1.60
     eliminar
    1.60
     obesidad
    1.60
     countDown
    1.59
    Activations Density 0.029%

    No Known Activations