© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115513
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    があります
    -1.55
    や
    -1.48
    と
    -1.45
    を
    -1.43
    などの
    -1.31
    これは
    -1.29
    。。。。
    -1.28
    がある
    -1.27
    !!!
    -1.24
    总之
    -1.22
    POSITIVE LOGITS
    0
    1.73
    為に
    1.70
    んですね
    1.65
    のですね
    1.52
     différentes
    1.49
    /
    1.41
     verschillende
    1.41
     different
    1.31
    ようになって
    1.30
    にします
    1.29
    Activations Density 0.203%

    No Known Activations