© 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. 22-GEMMASCOPE-RES-131K
    4. 344
    Prev
    Next
    INDEX
    Explanations

    words before punctuation or specific nouns

    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
     it
    -1.92
     its
    -1.88
     this
    -1.77
     their
    -1.69
     some
    -1.55
     only
    -1.55
     any
    -1.50
     or
    -1.47
     what
    -1.38
     those
    -1.35
    POSITIVE LOGITS
     grotte
    1.13
     Middlesbrough
    1.12
     Xavi
    1.10
     actuels
    1.10
    却没有
    1.10
     niečo
    1.10
     našich
    1.09
     deose
    1.09
     pollo
    1.08
     exasper
    1.07
    Activations Density 0.005%

    No Known Activations