© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79687
    Prev
    Next
    INDEX
    Explanations

    disruptive continuity conflicts

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

    The neuron fires on semantically “contentful” words (nouns, adjectives, verbs, and other non‐function words), ignoring common stop 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
     ویتامین
    -0.89
    Mandatory
    -0.85
     utilisent
    -0.82
    净化
    -0.82
    INCLUDES
    -0.79
    ḗ
    -0.79
    OKAY
    -0.79
    écoute
    -0.77
    ifiable
    -0.77
     disagre
    -0.77
    POSITIVE LOGITS
     continuity
    1.45
    continuity
    1.28
     stability
    1.18
    Continuity
    1.08
     consistency
    1.02
     destabili
    1.02
     Dadurch
    0.98
    önster
    0.96
     time
    0.96
     each
    0.92
    Activations Density 0.052%

    No Known Activations