© 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. 92111
    Prev
    Next
    INDEX
    Explanations

    code methods and objects

    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
    primarily
    -0.98
    mainly
    -0.95
     nedenle
    -0.90
    ILLO
    -0.89
     principalement
    -0.85
    directly
    -0.85
    шков
    -0.85
    وردی
    -0.85
    possibly
    -0.84
     inoxid
    -0.83
    POSITIVE LOGITS
     by
    2.08
     or
    1.45
     или
    0.86
    ремен
    0.84
     their
    0.84
     enhancing
    0.84
     cocción
    0.81
     prestigious
    0.80
    всегда
    0.78
    Parque
    0.78
    Activations Density 0.007%

    No Known Activations