© 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. 1207
    Prev
    Next
    INDEX
    Explanations

    imperative advice to reader

    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
    nya
    0.95
    Ad
    0.92
    elve
    0.91
    Auf
    0.87
    although
    0.87
    Van
    0.86
    ↵
    0.85
    non
    0.82
    ಹ
    0.81
    Certain
    0.80
    POSITIVE LOGITS
     yourself
    1.95
     yourselves
    1.83
     Yourself
    1.79
     jezelf
    1.54
    yourself
    1.46
    િંગ
    1.39
     نفسك
    1.31
     thys
    1.30
    ՛
    1.28
     możesz
    1.28
    Activations Density 0.826%

    No Known Activations