© 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. 156394
    Prev
    Next
    INDEX
    Explanations

    your words, enthusiasm, knowledge, memory, laws

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

    Mona Lisa

    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
    ৯০
    0.47
    চন্দ্রের
    0.46
     Hotspur
    0.45
    চন্দ্র
    0.45
    ν
    0.45
    釭
    0.45
    োর
    0.44
     Consequences
    0.44
     Mistakes
    0.44
    нансо
    0.43
    POSITIVE LOGITS
    debut
    0.47
     حدی
    0.46
    rones
    0.44
     위
    0.44
     市場
    0.43
     圖
    0.43
    rei
    0.43
     マー
    0.43
    python
    0.43
    kti
    0.43
    Activations Density 0.000%

    No Known Activations