© 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. 82979
    Prev
    Next
    INDEX
    Explanations

    phrases, buy, output, effects, key, calls, update, offices, list, cost

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

    The neuron selectively activates on content‐bearing, topic–specific nouns (e.g. “phrases,” “output,” “effects,” “pointers,” “calls,” “Best buy”).

    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
    esség
    -1.09
     relativement
    -1.06
     моей
    -1.02
     suficientemente
    -1.02
     вони
    -1.01
     нашей
    -0.98
     tenemos
    -0.97
     THEY
    -0.95
    they
    -0.94
     년
    -0.94
    POSITIVE LOGITS
     them
    2.58
     their
    2.22
     the
    2.17
     your
    2.03
     his
    1.97
     those
    1.91
     it
    1.78
     some
    1.73
     him
    1.70
     everything
    1.69
    Activations Density 0.224%

    No Known Activations