© 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. 22-GEMMASCOPE-RES-131K
    7. 71270
    Prev
    Next
    INDEX
    Explanations

    tactical analysis preparation

    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_22/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
     componente
    -1.21
    Interment
    -1.08
     fase
    -1.08
    fusions
    -1.07
     ingrediente
    -1.03
    受欢迎
    -1.02
     Uncertain
    -1.02
     sombra
    -1.02
    chappen
    -1.02
    anglement
    -1.00
    POSITIVE LOGITS
     analysis
    1.58
     analisar
    1.34
    analysis
    1.31
     observed
    1.30
     často
    1.29
     analyzed
    1.25
     analyzing
    1.25
     rewatch
    1.20
     Analysis
    1.19
    分析
    1.19
    Activations Density 0.021%

    No Known Activations