© 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. 38532
    Prev
    Next
    INDEX
    Explanations

    words starting with Sh

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on the sequence “Sh” at the start of names or identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     et
    -0.85
    階段
    -0.84
    が
    -0.84
    in
    -0.82
     all
    -0.79
    there
    -0.79
    ten
    -0.77
    を
    -0.75
     才
    -0.75
     took
    -0.75
    POSITIVE LOGITS
     sh
    1.36
     Sh
    1.34
    Sh
    1.33
    sh
    1.00
     türkiye
    0.98
    maksud
    0.98
     Шу
    0.97
    ्टी
    0.97
     bross
    0.96
     glisser
    0.96
    Activations Density 0.018%

    No Known Activations