© 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. 110977
    Prev
    Next
    INDEX
    Explanations

    sentence punctuation and the start of new clauses

    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
     although
    -1.21
     because
    -1.02
     without
    -1.01
     there
    -0.98
    although
    -0.96
     still
    -0.94
    still
    -0.94
     despite
    -0.88
     Although
    -0.84
    雖然
    -0.82
    POSITIVE LOGITS
     WRONG
    2.50
     Wrong
    2.38
    Wrong
    2.30
    WRONG
    2.16
     wrong
    2.16
    wrong
    2.00
     boy
    1.63
    Turns
    1.63
     Turns
    1.61
    実際
    1.52
    Activations Density 0.047%

    No Known Activations