© 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. 136001
    Prev
    Next
    INDEX
    Explanations

    MCT title

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

    hair, age, secrets, how-to, versions

    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
     ມີ
    0.55
     Chile
    0.47
     он
    0.47
    น
    0.46
     toug
    0.46
     лучше
    0.46
     direito
    0.46
     giri
    0.46
     мое
    0.45
     teri
    0.45
    POSITIVE LOGITS
    ة
    0.50
    創建
    0.48
    媽
    0.47
    nehmens
    0.45
    えると
    0.43
    hamburger
    0.42
    牆
    0.42
    就知道
    0.42
    anoic
    0.42
    Calculation
    0.41
    Activations Density 0.000%

    No Known Activations