© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128421
    Prev
    Next
    INDEX
    Explanations

    The neuron fires most strongly on words that express requirement, necessity, or obligation (e.g. “requires,” “needs,” “add,” “sufficient,” “physically,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    dates and time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     erneu
    -0.93
    стно
    -0.91
    μμ
    -0.85
     présence
    -0.85
     Taehyung
    -0.85
     Leggings
    -0.84
     kuasa
    -0.84
     थे
    -0.83
    的法
    -0.83
     salvador
    -0.83
    POSITIVE LOGITS
     skill
    1.23
     individuals
    1.21
     young
    1.16
     career
    1.12
     job
    1.09
     individual
    1.05
     skills
    1.04
     هؤلاء
    0.96
    คนที่
    0.96
     groups
    0.96
    Activations Density 0.168%

    No Known Activations