© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38853
    Prev
    Next
    INDEX
    Explanations

    conclusions and outcomes

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

    This neuron fires on prominent topic keywords (often in titles or headings) found in technical or scientific texts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    recently
    -1.09
     TAMBIÉN
    -1.02
     TAMBÉM
    -0.97
    Recently
    -0.93
    ifiquement
    -0.91
     omdat
    -0.90
    specially
    -0.90
     également
    -0.90
    وحة
    -0.90
    odacty
    -0.85
    POSITIVE LOGITS
     thus
    1.84
     then
    1.36
    就这样
    1.34
    これで
    1.33
     dermed
    1.28
    就此
    1.27
    Таким
    1.16
     now
    1.12
     finally
    1.10
     voila
    1.10
    Activations Density 0.039%

    No Known Activations