© 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. 87583
    Prev
    Next
    INDEX
    Explanations

    death

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

    process analysis/planning

    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
    󰡕
    0.47
     😘
    0.46
    🦳
    0.45
     lelaki
    0.45
    😠
    0.45
     masquer
    0.44
     🥰
    0.43
    洍
    0.43
     പഴ
    0.43
     kvalitet
    0.43
    POSITIVE LOGITS
    sc
    0.43
    愷
    0.41
    she
    0.41
     Fortuna
    0.40
    rim
    0.40
    李
    0.39
    ﺼ
    0.39
    只要
    0.39
    wild
    0.39
    hire
    0.38
    Activations Density 0.000%

    No Known Activations