© 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. 103449
    Prev
    Next
    INDEX
    Explanations

    programming value

    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
     vastly
    -1.24
    ◨
    -1.21
    岿
    -1.14
     niega
    -1.11
     stupidly
    -1.10
     新聞
    -1.09
     needlessly
    -1.07
     liquido
    -1.05
     realizó
    -1.05
     lampada
    -1.04
    POSITIVE LOGITS
     
    1.54
     proposition
    1.42
    값
    1.32
     值
    1.31
     judgments
    1.27
    域
    1.23
    在他的
    1.11
     tetapi
    1.10
     donc
    1.08
    этому
    1.08
    Activations Density 0.076%

    No Known Activations