© 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. 11508
    Prev
    Next
    INDEX
    Explanations

    children and childhood

    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
    čaj
    2.44
    тации
    2.09
     depleted
    2.01
    untlet
    1.99
     walmart
    1.98
    в
    1.93
     childhood
    1.93
     neck
    1.92
     گیری
    1.92
    जूद
    1.91
    POSITIVE LOGITS
    न
    2.38
    ല്ലാം
    2.25
    们的
    2.22
    م
    2.21
    siniz
    2.16
    க்
    2.11
    ям
    2.08
    lijke
    2.07
    روس
    2.02
    ઉન
    2.01
    Activations Density 0.035%

    No Known Activations