© 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. 34-GEMMASCOPE-RES-131K
    7. 102926
    Prev
    Next
    INDEX
    Explanations

    proper nouns and acronyms

    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_34/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
    よくある
    -1.29
    ώ
    -1.26
    苙
    -1.14
    ウチ
    -1.08
     turisti
    -1.08
     nozze
    -1.08
    そも
    -1.07
    ꒪
    -1.07
     позволит
    -1.06
    さんです
    -1.06
    POSITIVE LOGITS
     entweder
    1.24
    preneur
    1.16
     menyampaikan
    1.11
    brews
    1.10
     mengingatkan
    1.06
     olika
    1.06
     différentes
    1.03
    stricken
    1.01
     verschiedene
    1.01
    ًا
    1.01
    Activations Density 0.253%

    No Known Activations