© 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. 22-GEMMASCOPE-RES-131K
    7. 98286
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and states

    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_22/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
     will
    -2.19
     at
    -2.14
     as
    -1.89
     in
    -1.77
     this
    -1.70
     to
    -1.69
     on
    -1.63
     it
    -1.63
     there
    -1.60
     when
    -1.59
    POSITIVE LOGITS
     personnaliser
    1.68
     faciliter
    1.55
     favoriser
    1.54
     fonctionnent
    1.48
     énorm
    1.47
    很赞
    1.45
    țele
    1.43
     diriger
    1.42
     vermel
    1.41
     offrir
    1.41
    Activations Density 0.059%

    No Known Activations