© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14220
    Prev
    Next
    INDEX
    Explanations

    at the start of phrases

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

    at its core/heart

    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_16k_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
     recollections
    0.47
     adduced
    0.42
     প্রসঙ্গে
    0.42
     irregularities
    0.41
     hampers
    0.41
     misfortunes
    0.39
    ￳
    0.39
    setStyle
    0.39
    の結果
    0.38
    選擇
    0.38
    POSITIVE LOGITS
     rit
    0.40
    SizeBytes
    0.39
    MBA
    0.38
     Yet
    0.38
    στό
    0.38
    ictus
    0.38
    ventus
    0.38
    大约
    0.38
     oficialmente
    0.37
    <%@
    0.37
    Activations Density 0.108%

    No Known Activations