© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83197
    Prev
    Next
    INDEX
    Explanations

    nonparametric, non-asymptotic estimators

    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_34/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
    hame
    -0.78
    вам
    -0.76
     danach
    -0.75
    Ei
    -0.72
    demo
    -0.71
    Spreadsheet
    -0.71
    hopper
    -0.69
     स्व
    -0.69
    minist
    -0.68
     wait
    -0.68
    POSITIVE LOGITS
    checkable
    0.83
     mediu
    0.81
    агностика
    0.81
    pří
    0.80
    Какой
    0.79
     限
    0.79
    ꯴
    0.79
    ularis
    0.77
     pelic
    0.77
     fantasi
    0.76
    Activations Density 0.040%

    No Known Activations