© 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. 22429
    Prev
    Next
    INDEX
    Explanations

    appending data or variables

    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
     promove
    -1.66
    
    -1.65
     acclaimed
    -1.63
    .
    -1.62
     pertence
    -1.59
     podrás
    -1.58
     وإ
    -1.53
     entram
    -1.52
    лением
    -1.52
    秾
    -1.52
    POSITIVE LOGITS
    -”
    1.79
    Since
    1.75
    after
    1.68
    Despite
    1.67
     квітня
    1.66
     haphazard
    1.66
    After
    1.64
     guapos
    1.62
    Shortly
    1.62
    .”
    1.60
    Activations Density 0.008%

    No Known Activations