© 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. 10-GEMMASCOPE-RES-131K
    7. 120008
    Prev
    Next
    INDEX
    Explanations

    leading to introduction

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

    The neuron activates on words expressing urgency or haste (e.g. “rush,” “hurry”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     =
    -1.50
    2
    -1.48
    Bigr
    -1.48
     "...
    -1.39
    3
    -1.38
    どうしても
    -1.34
     always
    -1.34
     or
    -1.33
     nonetheless
    -1.33
     nevertheless
    -1.31
    POSITIVE LOGITS
     Româ
    1.45
    耳边
    1.40
    они
    1.39
    颪
    1.38
    GIVEREF
    1.35
     fatis
    1.34
     chiamato
    1.31
    ksjoner
    1.29
     kuna
    1.29
    JoinColumn
    1.29
    Activations Density 0.139%

    No Known Activations