© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116011
    Prev
    Next
    INDEX
    Explanations

    words like 're' or 'ti' or 'ca'

    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
    e
    -1.18
    n
    -1.06
    y
    -1.02
    an
    -0.96
    p
    -0.95
    v
    -0.94
    ו
    -0.94
    z
    -0.92
    k
    -0.92
    ん
    -0.88
    POSITIVE LOGITS
     sichere
    1.01
     traditionelle
    0.98
     heutigen
    0.94
     erfolgreiche
    0.93
     heutige
    0.90
     grüne
    0.88
    тня
    0.85
     klassische
    0.85
     Ouvrez
    0.84
     teaching
    0.80
    Activations Density 0.057%

    No Known Activations