© 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. 83353
    Prev
    Next
    INDEX
    Explanations

    null message values

    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
     även
    -1.03
     גם
    -0.84
     myös
    -0.82
     tudi
    -0.82
     وبعد
    -0.80
    лии
    -0.80
     seulement
    -0.79
    also
    -0.79
    deres
    -0.78
    non
    -0.77
    POSITIVE LOGITS
     nothing
    4.00
     NULL
    3.97
     None
    3.83
     nullptr
    3.81
     none
    3.81
     null
    3.61
    NULL
    3.59
    None
    3.45
    nullptr
    3.31
     nil
    3.11
    Activations Density 0.034%

    No Known Activations