© 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. 25383
    Prev
    Next
    INDEX
    Explanations

    disorder, imperfection, or irregularity

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

    The neuron fires on words that express disorder, irregularity, or lack of structure (e.g. disorganized, imperfect, irregular, indiscriminately, contradictory).

    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
    无聊
    -0.99
     rasa
    -0.97
     erforder
    -0.96
    ushes
    -0.96
    OLVED
    -0.95
    ÊNCIAS
    -0.94
    んですか
    -0.94
    地味
    -0.94
    ítmény
    -0.93
     Veränderung
    -0.93
    POSITIVE LOGITS
     chaotic
    1.36
     imperfect
    1.24
     irregular
    1.24
     haphazard
    1.18
     irregularly
    1.14
     messy
    1.09
     erratic
    1.02
     irregularity
    1.00
     imperfectly
    0.99
    irregular
    0.98
    Activations Density 0.092%

    No Known Activations