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

    Neuronpedia

    Jacobian LensNEW
    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. 7618
    Prev
    Next
    INDEX
    Explanations

    alternative paths

    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
    ر
    1.69
     scour
    1.64
     размеров
    1.64
     perimeter
    1.60
    шок
    1.60
     собой
    1.56
    ⅝
    1.49
    態
    1.47
     vacuoles
    1.47
     true
    1.46
    POSITIVE LOGITS
     paths
    2.72
     pathways
    2.32
     caminos
    2.05
    paths
    1.95
     path
    1.89
    path
    1.84
     Paths
    1.81
     pathway
    1.80
     filePath
    1.76
    WAY
    1.74
    Activations Density 0.470%

    No Known Activations