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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118980
    Prev
    Next
    INDEX
    Explanations

    Sass, Kirby, Object, Javier

    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
    createTextNode
    -1.02
    šné
    -1.00
    setLayoutManager
    -0.94
    setLayoutParams
    -0.90
    devServer
    -0.88
     still
    -0.88
     escapar
    -0.87
    日起
    -0.84
    TextUtils
    -0.82
    avimas
    -0.82
    POSITIVE LOGITS
    )#
    0.96
    ственном
    0.93
     dokumenti
    0.92
    ↵
    0.91
     kalt
    0.90
     capitulo
    0.89
    dubbo
    0.89
    Даже
    0.86
     generell
    0.86
    #
    0.85
    Activations Density 0.004%

    No Known Activations