© 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. 1417
    Prev
    Next
    INDEX
    Explanations

    sentence, prison, or jail

    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
     পূজা
    0.71
     রেজ
    0.68
     Colombeau
    0.68
    囃
    0.66
     قنات
    0.66
     वेडिंग
    0.66
     рекла
    0.66
     phun
    0.65
    洽
    0.64
     Dais
    0.64
    POSITIVE LOGITS
     prison
    4.06
     Prison
    3.75
     jail
    3.75
    Prison
    3.73
     prisoners
    3.71
     prisoner
    3.71
     prisons
    3.69
    prison
    3.69
     incarcerated
    3.56
     imprisonment
    3.52
    Activations Density 0.699%

    No Known Activations