© 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. 118141
    Prev
    Next
    INDEX
    Explanations

    null or none 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
     også
    -1.09
     właśnie
    -1.06
     myös
    -1.03
     opravdu
    -1.01
     również
    -0.96
     их
    -0.95
    шет
    -0.95
     också
    -0.95
    しちゃ
    -0.94
     vraiment
    -0.92
    POSITIVE LOGITS
     null
    3.17
     NULL
    2.17
    null
    2.08
     nothing
    1.82
     etc
    1.81
     nullptr
    1.72
    NULL
    1.58
    Null
    1.55
     None
    1.47
     nil
    1.45
    Activations Density 0.009%

    No Known Activations