© 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. 43134
    Prev
    Next
    INDEX
    Explanations

    other and another

    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
     той
    -1.53
    それでは
    -1.41
     where
    -1.39
    遄
    -1.39
    ྂ
    -1.37
    
    -1.36
    ністю
    -1.34
    AL
    -1.34
     =
    -1.32
    ommation
    -1.31
    POSITIVE LOGITS
    "
    1.76
    ى
    1.70
    卺
    1.66
    ми
    1.64
     produktu
    1.63
     οποία
    1.62
     („
    1.59
    ``
    1.52
    ementara
    1.49
    konstru
    1.48
    Activations Density 0.020%

    No Known Activations