© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73207
    Prev
    Next
    INDEX
    Explanations

    slavery, bribery, bravery, captivity, nudity

    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
    '
    -3.25
    ar
    -2.91
    好吃的
    -2.55
    S
    -2.41
    熥
    -2.34
    ︕
    -2.34
    姌
    -2.31
    ant
    -2.27
     είναι
    -2.23
    癶
    -2.19
    POSITIVE LOGITS
    骜
    2.77
    觏
    2.64
    驁
    2.45
    舠
    2.42
     geringen
    2.34
    忖
    2.33
    .
    2.30
    อย่างไร
    2.30
     Erwart
    2.30
     comical
    2.25
    Activations Density 0.001%

    No Known Activations