© 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. 65198
    Prev
    Next
    INDEX
    Explanations

    code and citations

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

    The neuron activates on HTML table cell tags (i.e. `<td>` elements).

    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
     \
    -2.53
     "
    -2.02
     “
    -1.95
     C
    -1.84
     R
    -1.76
     
    -1.73
     A
    -1.72
     ''
    -1.72
    T
    -1.65
     luchando
    -1.62
    POSITIVE LOGITS
     funcione
    1.63
    \
    1.62
     dieß
    1.59
     if
    1.52
    或者
    1.48
     campañas
    1.48
    1.46
    espero
    1.45
     WONDER
    1.43
     maglia
    1.42
    Activations Density 0.017%
    No Known Activations