© 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. 59181
    Prev
    Next
    INDEX
    Explanations

    ending or removal

    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
    屢
    -1.81
     availa
    -1.81
    If
    -1.74
     supremo
    -1.74
     HOY
    -1.70
     階段
    -1.61
     CHIL
    -1.61
    in
    -1.57
    墮
    -1.52
     ZU
    -1.49
    POSITIVE LOGITS
    
    1.80
    想必
    1.76
    ༈
    1.66
    iyor
    1.65
    也
    1.62
    
    1.59
     frases
    1.59
    ])){
    1.56
    知道
    1.55
    蒾
    1.52
    Activations Density 0.004%

    No Known Activations