© 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. 91306
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     började
    -0.90
    Filosof
    -0.83
    Hanya
    -0.82
    哪裡
    -0.81
    anyahu
    -0.81
    дыду
    -0.81
     называется
    -0.79
     Deutsche
    -0.79
     only
    -0.79
     Пере
    -0.79
    POSITIVE LOGITS
     article
    0.88
    丘
    0.84
     Locked
    0.80
    వ
    0.79
     publication
    0.79
     procesador
    0.78
    <0x9D>
    0.77
     لوله
    0.76
    چرخ
    0.76
    opathie
    0.75
    Activations Density 0.051%

    No Known Activations