© 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. 38728
    Prev
    Next
    INDEX
    Explanations

    both or between

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

    The neuron strongly lights up on content‐bearing words—especially common nouns (often plurals) and other semantically important terms—while ignoring grammatical function 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_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
     Counter
    -0.84
     converse
    -0.82
    9
    -0.81
    Ẽ
    -0.80
     lia
    -0.80
     limp
    -0.80
     exo
    -0.80
     Plu
    -0.79
     receptive
    -0.79
     Integral
    -0.78
    POSITIVE LOGITS
     both
    2.08
     their
    1.75
     Both
    1.70
    Both
    1.70
     between
    1.66
     beider
    1.59
     दोनों
    1.59
    both
    1.48
     keduanya
    1.48
    Between
    1.48
    Activations Density 0.124%

    No Known Activations