© 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. 10-GEMMASCOPE-RES-131K
    7. 1656
    Prev
    Next
    INDEX
    Explanations

    fundamental characteristics or issues

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

    The neuron fires on phrases describing major or fundamental structural shifts or changes (e.g. “seismic shifts,” “structural change,” “fundamental changes”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ınız
    -1.59
     Other
    -1.57
     Another
    -1.54
     ?
    -1.53
     Lainnya
    -1.50
    珖
    -1.47
    뿅
    -1.43
     hilsen
    -1.42
     scelta
    -1.41
     interpretar
    -1.41
    POSITIVE LOGITS
     that
    1.91
     fundament
    1.51
    \
    1.48
     therefore
    1.43
    <strong>
    1.40
    ↵
    1.37
    であり
    1.37
     funda
    1.36
     
    1.33
    ton
    1.30
    Activations Density 0.039%

    No Known Activations