© 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. 10-GEMMASCOPE-RES-131K
    7. 66409
    Prev
    Next
    INDEX
    Explanations

    comparisons to other things

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

    The neuron detects comparative statistical phrases that reference “other” groups or types—especially constructions like “other X groups” or “that of other cell types.”

    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
     about
    -1.80
     as
    -1.62
     along
    -1.55
    </b>
    -1.54
     worin
    -1.48
     not
    -1.47
     worauf
    -1.47
     through
    -1.46
    かもし
    -1.45
     need
    -1.41
    POSITIVE LOGITS
    ſſel
    1.68
    autres
    1.63
     chère
    1.53
     graciosos
    1.53
    ‌های
    1.44
     mogen
    1.43
     finos
    1.41
     vann
    1.40
     réalisateur
    1.39
     generell
    1.38
    Activations Density 0.049%

    No Known Activations