© 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. 244838
    Prev
    Next
    INDEX
    Explanations

    fat cells

    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
    🖼
    0.46
     chữ
    0.42
    ထား
    0.42
    ാം
    0.40
     thảo
    0.40
    样式
    0.40
     లేదా
    0.40
     প্রবন্ধ
    0.39
     কিংবা
    0.39
     অথবা
    0.39
    POSITIVE LOGITS
     т
    0.53
     терито
    0.50
     он
    0.48
     норма
    0.47
     estuv
    0.46
     венти
    0.46
     equipado
    0.45
     adequado
    0.45
     зем
    0.45
     туристи
    0.45
    Activations Density 0.001%

    No Known Activations