© 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. 15669
    Prev
    Next
    INDEX
    Explanations

    priority, priorities

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

    The neuron fires whenever it sees the word “priority.”

    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
    ↵↵
    -2.84
    </i>
    -2.34
     we
    -2.28
     BUT
    -2.02
     […]
    -2.02
     avowed
    -2.00
     aumenta
    -2.00
     multitudes
    -1.98
    }$.
    -1.98
     actualmente
    -1.96
    POSITIVE LOGITS
     berge
    2.44
    鮠
    2.25
    ”،
    2.19
    ！！”
    2.16
    趼
    2.06
     kalem
    2.05
    巿
    2.05
     sibuk
    2.03
    ⢓
    2.03
    ！！！”
    2.02
    Activations Density 0.005%

    No Known Activations