© 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. 10-GEMMASCOPE-RES-131K
    7. 90464
    Prev
    Next
    INDEX
    Explanations

    time and changes

    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_10/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
     no
    -1.54
    פות
    -1.45
    acheteur
    -1.42
     入力
    -1.41
     anfangs
    -1.40
    ANDUM
    -1.31
    ureusement
    -1.30
     derzeit
    -1.29
     to
    -1.28
    cayaan
    -1.27
    POSITIVE LOGITS
    ,"
    1.43
    ."
    1.42
     szczeg
    1.40
     anadolu
    1.37
    AfterViewInit
    1.35
     türk
    1.33
    哒
    1.31
    <mask>
    1.30
    /////////////
    1.30
    jadwal
    1.29
    Activations Density 0.057%

    No Known Activations