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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10898
    Prev
    Next
    INDEX
    Explanations

    next followed by time

    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_10/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
    灕
    -1.72
     it
    -1.60
    *),
    -1.52
    muñ
    -1.51
    OUTUBE
    -1.47
     and
    -1.47
     städ
    -1.47
    复制代码
    -1.46
     gevallen
    -1.45
    迨
    -1.45
    POSITIVE LOGITS
    t
    1.50
     afirma
    1.48
    あまり
    1.48
     обраща
    1.41
     him
    1.40
    r
    1.39
     suena
    1.33
     conversaciones
    1.30
    しばらく
    1.30
    買い物
    1.30
    Activations Density 0.007%

    No Known Activations