© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32851
    Prev
    Next
    INDEX
    Explanations

    numbers and increments

    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
     explain
    -0.79
    StringLen
    -0.75
    spunk
    -0.74
    簿
    -0.73
    出し
    -0.72
    യും
    -0.72
    랑
    -0.71
     romances
    -0.71
    زين
    -0.71
    <0xA0>
    -0.70
    POSITIVE LOGITS
     increments
    2.77
     increment
    2.45
    increment
    2.23
    increments
    2.19
    Increment
    1.99
     incremental
    1.92
     Increment
    1.92
     Incre
    1.87
     step
    1.87
    INCREMENT
    1.73
    Activations Density 0.045%

    No Known Activations