© 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. 23797
    Prev
    Next
    INDEX
    Explanations

    suffixes like -plexy, -rium, -tion, -mia

    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
     and
    -3.59
     or
    -2.94
     at
    -2.23
     with
    -2.22
     any
    -2.20
     this
    -2.11
     from
    -2.05
     new
    -2.03
     both
    -2.02
     it
    -1.99
    POSITIVE LOGITS
    perhaps
    2.09
    despite
    2.02
    whose
    1.92
    possibly
    1.84
    particularly
    1.80
     perpé
    1.75
    probably
    1.73
     fiasco
    1.73
    primarily
    1.71
    薷
    1.71
    Activations Density 0.197%

    No Known Activations