© 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. 34-GEMMASCOPE-RES-131K
    7. 110871
    Prev
    Next
    INDEX
    Explanations

    sentence-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_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
     epitom
    -1.84
     profoundly
    -1.80
     garner
    -1.73
     undeniably
    -1.68
     focusing
    -1.67
     revital
    -1.66
     multifaceted
    -1.65
     attaining
    -1.63
     amidst
    -1.63
     all
    -1.63
    POSITIVE LOGITS
    ,,,
    2.09
     Dinas
    2.02
    ,,
    1.83
    ,,,,
    1.83
     !!!!
    1.81
    !!!!!!!
    1.80
     tranquil
    1.75
    ,.
    1.73
    すっ
    1.70
     trois
    1.70
    Activations Density 0.052%

    No Known Activations