© 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. 60616
    Prev
    Next
    INDEX
    Explanations

    code formatting or markup

    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
    も良い
    -1.84
    もいい
    -1.53
    italien
    -1.53
     chefe
    -1.47
     desagrad
    -1.46
     governador
    -1.46
     Mulher
    -1.45
    vocable
    -1.41
    也非常
    -1.41
     istor
    -1.40
    POSITIVE LOGITS
    es
    1.87
    D
    1.78
    to
    1.69
    is
    1.52
    En
    1.49
    all
    1.47
    Be
    1.46
    get
    1.44
    De
    1.44
    create
    1.41
    Activations Density 0.021%

    No Known Activations