© 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. 93152
    Prev
    Next
    INDEX
    Explanations

    end of sentence 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
    sterious
    -1.00
    无聊
    -0.98
     ankara
    -0.89
     "|
    -0.88
    ânea
    -0.87
     Leurs
    -0.87
     colonia
    -0.87
    もう少し
    -0.86
    仕上がり
    -0.86
     dataTable
    -0.83
    POSITIVE LOGITS
     or
    1.19
     takie
    1.03
     peores
    0.97
     pintores
    0.90
    več
    0.90
    feitura
    0.89
     Vereinigten
    0.88
    一等
    0.88
     if
    0.84
    diali
    0.84
    Activations Density 0.051%

    No Known Activations