© 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. 82357
    Prev
    Next
    INDEX
    Explanations

    actions of groups

    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
     his
    -1.99
     them
    -1.94
     its
    -1.53
     jego
    -1.49
     myself
    -1.31
     själv
    -1.30
     yourself
    -1.28
     его
    -1.27
     них
    -1.17
     kendini
    -1.14
    POSITIVE LOGITS
     themselves
    5.28
    themselves
    3.25
     their
    2.83
     leurs
    2.39
    Their
    2.30
    他们的
    2.05
     themſelves
    2.03
    their
    1.95
     they
    1.85
     eivät
    1.78
    Activations Density 0.118%

    No Known Activations