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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110648
    Prev
    Next
    INDEX
    Explanations

    code identifiers after punctuation

    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
     as
    -1.37
     what
    -1.20
     for
    -1.18
     if
    -1.12
     desfile
    -1.04
     on
    -1.03
    !!!!!
    -1.02
     zobaczyć
    -1.01
     it
    -1.01
    トッピング
    -0.99
    POSITIVE LOGITS
    ㍉
    1.34
     perpé
    1.29
     maniere
    1.27
     estadía
    1.25
     éte
    1.24
    Fiz
    1.24
    
    1.20
     можуть
    1.18
     cóc
    1.17
    possibly
    1.16
    Activations Density 0.008%

    No Known Activations