© 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. 12126
    Prev
    Next
    INDEX
    Explanations

    code snippets and numbers

    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
     under
    -0.84
    ้อม
    -0.75
    MONITOR
    -0.71
     tiba
    -0.70
     Suède
    -0.69
     llam
    -0.68
     leren
    -0.68
    lish
    -0.68
     tours
    -0.67
    pandemic
    -0.66
    POSITIVE LOGITS
     pitbull
    0.75
     igneous
    0.69
     nemat
    0.68
     excru
    0.67
     chấm
    0.67
     SDM
    0.66
     générations
    0.65
     Krypto
    0.65
     plead
    0.64
     laboratoire
    0.64
    Activations Density 0.075%

    No Known Activations