© 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. 398
    Prev
    Next
    INDEX
    Explanations

    must be

    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
     necessary
    -0.98
     مدى
    -0.91
     mainly
    -0.90
    랄
    -0.90
     usually
    -0.89
    Всего
    -0.88
     nécessaire
    -0.85
    잃
    -0.85
    ͏
    -0.85
    要注意
    -0.83
    POSITIVE LOGITS
    才行
    1.14
    才能
    1.06
    才可以
    1.00
     mustn
    0.99
    however
    0.96
    才有
    0.92
     ooo
    0.91
    artney
    0.88
    ciens
    0.88
     aquesta
    0.88
    Activations Density 0.038%

    No Known Activations