© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8983
    Prev
    Next
    INDEX
    Explanations

    lesser

    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
    蠵
    -2.67
    
    -2.67
    鱨
    -2.64
     绒
    -2.63
    亖
    -2.58
    揠
    -2.55
    鈇
    -2.52
    魴
    -2.50
    🤕
    -2.44
    掼
    -2.42
    POSITIVE LOGITS
    ↵
    3.27
     That
    2.83
    "
    2.72
    that
    2.69
    what
    2.67
    7
    2.64
    </h3>
    2.64
    most
    2.59
    3
    2.58
    比起
    2.48
    Activations Density 0.005%

    No Known Activations