© 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. 70743
    Prev
    Next
    INDEX
    Explanations

    connecting clauses and lists

    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
     through
    -1.55
     especially
    -1.41
     Especially
    -1.26
     using
    -1.21
     during
    -1.18
     on
    -1.16
     without
    -1.12
     Depending
    -1.10
    стую
    -1.09
     in
    -1.05
    POSITIVE LOGITS
     they
    1.93
     are
    1.78
    either
    1.31
     theyre
    1.20
     were
    1.20
     They
    1.20
     eivät
    1.18
     entweder
    1.17
     هستند
    1.15
     themselves
    1.14
    Activations Density 0.073%

    No Known Activations