© 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. 87135
    Prev
    Next
    INDEX
    Explanations

    sentence endings followed by capitalized words

    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
     Dr
    -1.10
    Dr
    -1.09
    =?,
    -1.09
    According
    -0.98
    hc
    -0.96
    November
    -0.95
    とのこと
    -0.94
    Minister
    -0.93
     because
    -0.93
    February
    -0.93
    POSITIVE LOGITS
     aides
    1.34
     hours
    1.29
    mitsub
    1.05
     POLIT
    1.04
    Miro
    0.99
     incoming
    0.98
    Hours
    0.95
     mandatario
    0.94
     minutes
    0.94
    Giới
    0.94
    Activations Density 0.054%

    No Known Activations