© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 10068
    Prev
    Next
    INDEX
    Explanations

    It is

    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
     Perrin
    0.98
     winch
    0.96
    薏
    0.91
     serr
    0.91
     Hobbs
    0.91
    但在
    0.87
    <unused1700>
    0.86
    hrs
    0.86
     clot
    0.85
     Chiron
    0.83
    POSITIVE LOGITS
     gusto
    0.95
     за
    0.94
    다
    0.89
     trebui
    0.88
    べき
    0.85
    ية
    0.84
     индиви
    0.80
     segi
    0.79
    p
    0.78
     پڑ
    0.78
    Activations Density 0.030%

    No Known Activations