© 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. 29-GEMMASCOPE-2-RES-16K
    7. 964
    Prev
    Next
    INDEX
    Explanations

    URLs with path segments

    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_29_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
     diagonally
    0.94
     frail
    0.89
     rotated
    0.87
     any
    0.83
     obfusc
    0.82
    ◙
    0.82
     moves
    0.81
     attackers
    0.81
     unbalanced
    0.80
     ski
    0.79
    POSITIVE LOGITS
    article
    1.60
    articles
    1.60
    Articles
    1.56
    index
    1.51
    Article
    1.45
    category
    1.44
    Category
    1.37
    content
    1.36
    categories
    1.35
    #!
    1.31
    Activations Density 0.262%

    No Known Activations