© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 3476
    Prev
    Next
    INDEX
    Explanations

    specific numbers and units

    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
    に
    0.93
    बित
    0.92
     nuovo
    0.90
     étaient
    0.89
     ialah
    0.88
     duidelijk
    0.88
    为例
    0.87
     kembali
    0.85
     nový
    0.85
     são
    0.85
    POSITIVE LOGITS
    although
    0.96
     although
    0.87
    %.
    0.87
     ().
    0.84
    ().
    0.83
    while
    0.80
    .).
    0.79
    отя
    0.78
    unless
    0.77
    ».
    0.77
    Activations Density 0.258%

    No Known Activations