© 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. 8946
    Prev
    Next
    INDEX
    Explanations

    introducing new items

    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
    <unused2162>
    1.01
    <unused1910>
    0.94
    <unused458>
    0.92
    <unused1823>
    0.91
    መል
    0.91
    <unused249>
    0.90
     nCenters
    0.90
     seduce
    0.89
    <unused311>
    0.88
     saludable
    0.88
    POSITIVE LOGITS
     new
    0.86
     (
    0.80
     oss
    0.77
     W
    0.73
     नए
    0.71
     E
    0.71
     O
    0.69
     New
    0.68
     Pro
    0.67
     "
    0.66
    Activations Density 0.003%

    No Known Activations