© 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. 10-GEMMASCOPE-RES-131K
    4. 21704
    Prev
    Next
    INDEX
    Explanations

    numbers and counts of entities

    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
     only
    -1.48
     or
    -1.34
     perhaps
    -1.33
     might
    -1.32
    entown
    -1.31
     at
    -1.30
     an
    -1.28
    kür
    -1.27
     probably
    -1.27
     may
    -1.27
    POSITIVE LOGITS
     of
    1.48
    forKey
    1.32
     Synag
    1.31
    可以看到
    1.29
    <mask>
    1.28
     Dinas
    1.25
     Wasserstoff
    1.23
    )
    1.23
     Griechenland
    1.23
     who
    1.21
    Activations Density 0.296%

    No Known Activations