© 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. 42006
    Prev
    Next
    INDEX
    Explanations

    energy levels and spectrum

    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
    产生了
    -1.89
    鼉
    -1.88
    裥
    -1.77
     ニット
    -1.70
     the
    -1.65
     内衣
    -1.63
    provide
    -1.63
    the
    -1.61
     ity
    -1.61
     .......
    -1.59
    POSITIVE LOGITS
     of
    1.80
    .
    1.76
     bemerken
    1.59
     彈
    1.41
    อะไร
    1.39
    owulf
    1.38
     make
    1.36
     壓
    1.34
     gewisser
    1.32
     địch
    1.31
    Activations Density 0.026%

    No Known Activations