© 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. 25780
    Prev
    Next
    INDEX
    Explanations

    duration in places and states

    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
     helg
    -0.83
    MatInputModule
    -0.81
    Mine
    -0.81
     propias
    -0.81
    Ogni
    -0.79
    無く
    -0.79
    thm
    -0.79
    grunn
    -0.77
    ırs
    -0.75
    kman
    -0.75
    POSITIVE LOGITS
     all
    3.17
     всю
    2.42
     his
    2.36
     my
    2.31
     your
    2.05
     tüm
    1.78
     seluruh
    1.76
     toute
    1.70
     lifelong
    1.69
     tutta
    1.67
    Activations Density 0.039%

    No Known Activations