© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26755
    Prev
    Next
    INDEX
    Explanations

    respective, respectively

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

    The neuron consistently lights up on long, content-heavy or technical words—especially multi-syllabic nouns and adjectives (e.g. specific, subunit, recognized, polymer, methodology, shortcomings).

    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
    atay
    -0.85
    dì
    -0.83
     Orten
    -0.80
     metabolism
    -0.80
    Biografie
    -0.79
    횟
    -0.77
    ;'>
    -0.77
    ществует
    -0.75
    倉
    -0.74
     ajoutez
    -0.73
    POSITIVE LOGITS
     respective
    2.08
     respectively
    1.98
    それぞれ
    1.77
    respectively
    1.68
     jeweiligen
    1.51
    respective
    1.50
     rispet
    1.50
    分别是
    1.49
     respectivement
    1.47
    それぞれの
    1.35
    Activations Density 0.134%

    No Known Activations