© 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. 14145
    Prev
    Next
    INDEX
    Explanations

    should have + past participle

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

    This neuron fires on words that occur in perfect‐tense constructions (auxiliary “have/had” and their following past‐participle forms).

    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
    توضیحات
    -1.00
    Ингредиенты
    -1.00
    숱
    -1.00
    發表
    -0.99
     magnifiques
    -0.89
    után
    -0.89
    Apakah
    -0.88
    impinan
    -0.88
    非常に
    -0.87
    Какие
    -0.87
    POSITIVE LOGITS
     earlier
    1.31
     võib
    1.09
     predictions
    1.02
     предупре
    1.00
     warnings
    1.00
     instead
    0.96
    めた
    0.96
     второй
    0.95
    )!
    0.91
     aurait
    0.91
    Activations Density 0.021%

    No Known Activations