© 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. 2000
    Prev
    Next
    INDEX
    Explanations

    Bundle keys and values

    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
     then
    -2.41
     before
    -1.27
     тогда
    -1.24
    Then
    -1.15
     Then
    -1.13
     now
    -1.12
     então
    -1.09
     Daley
    -1.09
     سپس
    -1.07
     dann
    -1.06
    POSITIVE LOGITS
     each
    1.11
     which
    1.01
    Especificaciones
    0.94
     отличается
    0.93
    Each
    0.88
     will
    0.86
     einzelnen
    0.86
     tačiau
    0.85
    agisse
    0.84
     tandis
    0.84
    Activations Density 0.025%

    No Known Activations