© 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. 39561
    Prev
    Next
    INDEX
    Explanations

    ending punctuation

    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
     goûts
    -1.20
     Beweg
    -1.19
    フェイス
    -1.12
    completed
    -1.10
    のエ
    -1.09
     fér
    -1.08
     cél
    -1.07
     éta
    -1.06
    ajouter
    -1.05
     réve
    -1.05
    POSITIVE LOGITS
     had
    1.57
     because
    1.49
     has
    1.47
     but
    1.45
     they
    1.45
     will
    1.45
     really
    1.27
     actually
    1.24
     would
    1.21
     which
    1.19
    Activations Density 0.071%

    No Known Activations