© 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. 34-GEMMASCOPE-RES-131K
    7. 31693
    Prev
    Next
    INDEX
    Explanations

    content deleted or removed

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

    The neuron fires on passive‐voice verb phrases, i.e. forms of “to be” plus a past participle.

    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
    avoid
    -0.85
     Александра
    -0.85
    出典
    -0.82
    นด์
    -0.81
    OTT
    -0.81
     inauguración
    -0.78
    чни
    -0.77
     legalization
    -0.77
    %``
    -0.77
    ishments
    -0.77
    POSITIVE LOGITS
     deleted
    3.36
     delete
    3.09
     removed
    2.92
     deleting
    2.66
     remove
    2.64
     deletion
    2.59
     removal
    2.59
     deletes
    2.41
    删除
    2.36
     Delete
    2.27
    Activations Density 0.063%

    No Known Activations