© 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. 34-GEMMASCOPE-RES-131K
    7. 91389
    Prev
    Next
    INDEX
    Explanations

    separate or dissociate concepts

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

    The neuron fires on occurrences of auxiliary “be” verbs together with past participles or adjectives, i.e. passive-voice constructions.

    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
    tablir
    -0.80
     ytterligare
    -0.78
     собак
    -0.78
    ည်
    -0.78
     حوالي
    -0.77
     larynx
    -0.76
    藪
    -0.75
    expandindo
    -0.75
    лично
    -0.74
    Ramon
    -0.74
    POSITIVE LOGITS
     separable
    1.27
     sever
    1.25
     Sever
    1.20
    Sever
    1.16
     separ
    1.11
     severed
    1.10
     severance
    1.07
    sever
    1.00
    separ
    0.98
    SEVER
    0.96
    Activations Density 0.011%

    No Known Activations