© 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. 118072
    Prev
    Next
    INDEX
    Explanations

    anything else

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

    The neuron strongly activates on very common English words (e.g. “anything,” “nothing,” “else”), i.e. high‐frequency function/content words.

    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
     beberapa
    -1.00
     religieuses
    -0.97
     sebaik
    -0.94
    ждений
    -0.94
    どこか
    -0.93
     chré
    -0.93
     things
    -0.91
     Csv
    -0.91
     and
    -0.90
     entièrement
    -0.90
    POSITIVE LOGITS
     except
    1.60
     else
    1.59
     кроме
    1.45
     notable
    1.35
     noteworthy
    1.34
    except
    1.34
     besides
    1.33
     specific
    1.33
     significant
    1.30
     important
    1.27
    Activations Density 0.030%

    No Known Activations