© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1190
    Prev
    Next
    INDEX
    Explanations

    dark dancing themes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    踮
    0.81
    蹭
    0.74
    🧢
    0.73
     flattered
    0.71
     Semiconductors
    0.70
     modestly
    0.69
     confidentiality
    0.69
     እንቅስቃሴ
    0.68
    beginner
    0.67
    捋
    0.67
    POSITIVE LOGITS
     horrifying
    3.43
     horrific
    3.29
     gruesome
    3.10
     horrors
    3.04
     horrible
    2.93
     horrid
    2.90
     hideous
    2.89
     dreadful
    2.86
     horrendous
    2.85
     cruel
    2.81
    Activations Density 1.573%

    No Known Activations