© 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. 103902
    Prev
    Next
    INDEX
    Explanations

    Thanks followed by A:

    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
    ˣ
    -1.49
    EDEFAULT
    -1.45
    liters
    -1.42
     merve
    -1.36
    采用了
    -1.34
     dizaines
    -1.34
    ISME
    -1.31
    PACE
    -1.30
    形成了
    -1.29
    INESS
    -1.27
    POSITIVE LOGITS
    They
    1.78
    两个
    1.74
    Any
    1.57
    Not
    1.52
    would
    1.52
    ↵↵
    1.51
    Your
    1.50
    所有
    1.45
    Once
    1.45
    一个
    1.44
    Activations Density 0.037%

    No Known Activations