© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69176
    Prev
    Next
    INDEX
    Explanations

    hereinafter referred to as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Their
    -2.42
     THEIR
    -2.27
    ৄ
    -2.22
    逦
    -2.22
     který
    -2.13
    ляции
    -2.08
    一部分
    -2.08
    ਞ
    -2.05
    ⟞
    -2.05
     でも
    -1.99
    POSITIVE LOGITS
    ization
    2.28
    7
    2.16
     terlaris
    2.14
    л
    2.11
    ists
    2.06
    　　“
    2.05
    ities
    2.03
     Для
    2.02
    荻
    1.98
    在此
    1.96
    Activations Density 0.003%

    No Known Activations