© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 95223
    Prev
    Next
    INDEX
    Explanations

    death and imprisonment

    np_acts-logits-general · gemini-2.5-flash-lite

    negative sentiments or problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    传感
    0.66
    传感器
    0.60
    ാൻഡ്
    0.59
     permettent
    0.55
    赛事
    0.55
     sensorial
    0.55
    〰
    0.55
    িজে
    0.55
    🧜
    0.54
     seamlessly
    0.54
    POSITIVE LOGITS
     helpless
    0.62
     imprisonment
    0.59
     enmity
    0.58
     victims
    0.57
     hatred
    0.57
     murderous
    0.56
     died
    0.55
     imprison
    0.55
     death
    0.55
     Worse
    0.54
    Activations Density 0.000%

    No Known Activations