© 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. 75474
    Prev
    Next
    INDEX
    Explanations

    end of sentences or quotes

    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
     “…
    -1.23
     «
    -1.20
     ‘‘
    -1.11
     “...
    -1.05
     "...
    -1.05
    “…
    -0.91
    。「
    -0.91
     「
    -0.88
     “[
    -0.88
    —“
    -0.88
    POSITIVE LOGITS
    .”
    2.55
    ."
    2.27
    」
    2.02
    !”
    1.94
    """
    1.90
    !"
    1.87
    ",
    1.84
    ");
    1.84
    ?"
    1.71
    ?”
    1.70
    Activations Density 0.324%

    No Known Activations