© 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. 65914
    Prev
    Next
    INDEX
    Explanations

    numbers, slashes, dates, or 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
    şam
    -0.91
    xmlns
    -0.79
     debido
    -0.78
    ᱹ
    -0.75
    requestCode
    -0.75
    ape
    -0.74
     ureter
    -0.74
     rather
    -0.74
     entirety
    -0.74
    ENCIL
    -0.73
    POSITIVE LOGITS
    Добавлено
    0.79
    addView
    0.75
    romance
    0.73
     tiet
    0.72
     ultime
    0.72
    eriam
    0.72
    pricht
    0.71
     felpa
    0.71
    Engineers
    0.71
     Giuliano
    0.71
    Activations Density 0.195%

    No Known Activations